© 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. 78652
    Prev
    Next
    INDEX
    Explanations

    from

    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
    돌
    -0.07
     ethanol
    -0.07
    upplier
    -0.07
     suk
    -0.07
     след
    -0.07
     Different
    -0.06
    מספר
    -0.06
    投资项目
    -0.06
     HW
    -0.06
    .disconnect
    -0.06
    POSITIVE LOGITS
     NotImplemented
    0.08
    =label
    0.07
    POSITE
    0.07
    .toHexString
    0.07
    彗
    0.07
     Kits
    0.07
    .readAs
    0.06
     "@"
    0.06
    夹
    0.06
     VII
    0.06
    Activations Density 0.108%

    No Known Activations