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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 31021
    Prev
    Next
    INDEX
    Explanations

    government and representatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    相关人员
    -0.07
     Mag
    -0.07
    _Cmd
    -0.07
    (ARG
    -0.07
     SOC
    -0.07
    ☣
    -0.07
    最优
    -0.06
    [line
    -0.06
    务
    -0.06
     рег
    -0.06
    POSITIVE LOGITS
     Aristotle
    0.08
     Ernst
    0.07
    在内的
    0.07
    '],['
    0.07
    توي
    0.07
    );
    0.07
     college
    0.07
    伴侣
    0.07
    interpre
    0.07
    ነ
    0.07
    Activations Density 0.155%

    No Known Activations