© 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 EvalsExportsAPI 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. 113503
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act · gemini-2.0-flash

    references to domain-specific named entities and acronyms, especially formal document types and organization or place names in structured lists.

    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
     scaff
    -0.08
    饭店
    -0.07
     modifies
    -0.07
    _vehicle
    -0.07
    .library
    -0.07
     fluor
    -0.07
     execute
    -0.07
     Vy
    -0.07
     declar
    -0.07
    这款游戏
    -0.07
    POSITIVE LOGITS
     paused
    0.07
    重视
    0.07
    חום
    0.07
    ˖
    0.07
    きます
    0.07
    lots
    0.06
    elligent
    0.06
    ￠
    0.06
     다양한
    0.06
     opendir
    0.06
    Activations Density 10.810%

    No Known Activations