© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 49927
    Prev
    Next
    INDEX
    Explanations

    asking for help

    np_max-act · gemini-2.0-flash

    user help-seeking requests directed at the assistant, typically polite questions with first‑person objects and infinitive task descriptions across multiple languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    polite user requests for assistance to perform a task, especially phrased as direct questions (e.g., “can you help me…?”) across multiple languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kant
    -0.08
    ḑ
    -0.07
    .requireNonNull
    -0.07
     @$
    -0.07
    {-#
    -0.07
     astr
    -0.07
     السلطة
    -0.07
    ух
    -0.07
    垡
    -0.06
    scientific
    -0.06
    POSITIVE LOGITS
    搂
    0.07
    uring
    0.07
    콱
    0.07
     çıkan
    0.07
    レーション
    0.07
     ticking
    0.07
    Automation
    0.07
    ToolBar
    0.07
    nob
    0.07
     השירות
    0.06
    Activations Density 0.061%

    No Known Activations