© 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. 7-RESID-POST-AA
    11. 78845
    Prev
    Next
    INDEX
    Explanations

    file paths/URLs/code

    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
     Kö
    -0.09
    ]=$
    -0.07
    lijke
    -0.07
    颏
    -0.07
    另一个
    -0.07
     האישי
    -0.07
    藐
    -0.07
    先导
    -0.07
     deny
    -0.07
    可靠的
    -0.06
    POSITIVE LOGITS
    .Graphics
    0.08
     gente
    0.07
     portrayed
    0.07
     الناس
    0.07
    bab
    0.07
     الشباب
    0.07
     الجميع
    0.07
    ILES
    0.06
    _df
    0.06
    _sparse
    0.06
    Activations Density 0.001%

    No Known Activations