© 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. 19-RESID-POST-AA
    11. 70842
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    してください
    -0.08
     áo
    -0.07
     humano
    -0.07
    .Points
    -0.07
    깐
    -0.07
    过来
    -0.07
     escaped
    -0.07
     Kurd
    -0.07
    أن
    -0.07
     mourn
    -0.06
    POSITIVE LOGITS
     저
    0.07
    SETTINGS
    0.07
    impact
    0.07
    🏛
    0.07
     önlem
    0.06
    rollable
    0.06
    𬹼
    0.06
    (display
    0.06
     WAL
    0.06
    ꦭ
    0.06
    Activations Density 0.085%

    No Known Activations