© 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. 78367
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical texts

    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
    خ
    -0.07
    INDOW
    -0.07
    Anchor
    -0.07
     capitals
    -0.07
    空气中
    -0.07
    也知道
    -0.07
    امة
    -0.06
    ⭑
    -0.06
    amous
    -0.06
     Plate
    -0.06
    POSITIVE LOGITS
    สด
    0.08
    这么多
    0.08
    ovan
    0.07
    prefer
    0.07
    第二种
    0.07
     plurality
    0.07
     décid
    0.07
    .setPosition
    0.07
    Redirect
    0.07
    探测
    0.07
    Activations Density 0.059%

    No Known Activations