© 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 EvalsExportsAPI 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. 34447
    Prev
    Next
    INDEX
    Explanations

    lightweight

    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
    /trans
    -0.09
    請您
    -0.07
    №
    -0.07
    =db
    -0.07
    玢
    -0.07
    anal
    -0.07
    ل
    -0.07
    \Action
    -0.06
     CHO
    -0.06
    .MapPath
    -0.06
    POSITIVE LOGITS
    (len
    0.07
     mayoría
    0.07
     cuatro
    0.07
     leurs
    0.07
    ่าว
    0.07
    _w
    0.07
     protección
    0.07
     lev
    0.06
    /J
    0.06
     pits
    0.06
    Activations Density 0.005%

    No Known Activations