© 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. 40119
    Prev
    Next
    INDEX
    Explanations

    wood

    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
    耘
    -0.07
    課程
    -0.07
     fg
    -0.07
     diminish
    -0.07
    mdir
    -0.07
    一律
    -0.07
     preach
    -0.07
     Key
    -0.06
     koji
    -0.06
     ráp
    -0.06
    POSITIVE LOGITS
    出行
    0.07
    unting
    0.07
    intColor
    0.07
    طبيع
    0.07
    谢邀
    0.07
    星级酒店
    0.06
     grabbing
    0.06
    half
    0.06
    awl
    0.06
    报考
    0.06
    Activations Density 0.001%

    No Known Activations