© 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. 11-RESID-POST-AA
    11. 28921
    Prev
    Next
    INDEX
    Explanations

    Before

    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
    Henry
    -0.07
    Runs
    -0.07
    Company
    -0.07
     Ethnic
    -0.07
    ケット
    -0.07
    害
    -0.06
    豺
    -0.06
     bark
    -0.06
    執行
    -0.06
     punched
    -0.06
    POSITIVE LOGITS
    相对较
    0.07
    nze
    0.06
     différence
    0.06
     `,↵
    0.06
     lesb
    0.06
    ificantly
    0.06
    индивиду
    0.06
     Interracial
    0.06
     שאין
    0.06
    احتج
    0.06
    Activations Density 0.011%

    No Known Activations