© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30578
    Prev
    Next
    INDEX
    Explanations

    people

    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
    =end
    -0.08
     paperback
    -0.08
    Drive
    -0.08
     arcs
    -0.07
    wolf
    -0.07
    表述
    -0.07
    .error
    -0.07
    .sequence
    -0.07
     אביב
    -0.07
    いたします
    -0.07
    POSITIVE LOGITS
    ieg
    0.09
    地下室
    0.07
    беж
    0.07
    empl
    0.07
     кам
    0.07
    فاع
    0.07
     folks
    0.07
    epar
    0.07
     предпри
    0.07
    ukt
    0.07
    Activations Density 0.015%

    No Known Activations