© 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. 15-RESID-POST-AA
    11. 80092
    Prev
    Next
    INDEX
    Explanations

    scout

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="{!!
    -0.08
    ?action
    -0.07
     Adds
    -0.07
    瘅
    -0.07
     supper
    -0.07
     kepada
    -0.07
     marginRight
    -0.07
    endoza
    -0.07
    酽
    -0.07
     millionaire
    -0.07
    POSITIVE LOGITS
    目前已
    0.08
    _rf
    0.07
     нагруз
    0.07
     creation
    0.07
     rá
    0.07
    от
    0.07
    чи
    0.07
     лица
    0.07
    letal
    0.07
    olen
    0.07
    Activations Density 0.003%

    No Known Activations