© 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. 18035
    Prev
    Next
    INDEX
    Explanations

    life concepts

    np_max-act · gemini-2.0-flash

    mentions of geographic locations, tourist attractions, and travel-related descriptive terms (places, landmarks, sights).

    oai_token-act-pair · gpt-5-miniTriggered 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
    時代
    -0.07
     Though
    -0.07
    かなり
    -0.07
     perder
    -0.06
     경우에는
    -0.06
    (core
    -0.06
    ものは
    -0.06
    武汉市
    -0.06
    챈
    -0.06
     thí
    -0.06
    POSITIVE LOGITS
    '↵
    0.08
    智能化
    0.08
    package
    0.08
    ↵
    0.07
    果蔬
    0.07
    AutoresizingMask
    0.07
    .absolute
    0.07
    哑
    0.07
    "↵
    0.07
    �
    0.07
    Activations Density 11.095%

    No Known Activations