© 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. 7-RESID-POST-AA
    11. 80132
    Prev
    Next
    INDEX
    Explanations

    AL

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     widespread
    -0.07
    记录
    -0.07
     glm
    -0.07
    旗帜
    -0.07
    ?]
    -0.07
    名单
    -0.06
     кры
    -0.06
     melan
    -0.06
    peat
    -0.06
     Peng
    -0.06
    POSITIVE LOGITS
    逖
    0.08
    levant
    0.07
    הם
    0.07
    _interface
    0.07
    On
    0.07
    等奖
    0.07
     thôi
    0.07
    ,item
    0.07
     ريال
    0.06
     bailout
    0.06
    Activations Density 0.004%

    No Known Activations