© 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. 108199
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    òng
    -0.07
    ustainability
    -0.07
    particularly
    -0.07
    _call
    -0.07
    eci
    -0.06
    FRING
    -0.06
    ichel
    -0.06
    m
    -0.06
     international
    -0.06
    قدير
    -0.06
    POSITIVE LOGITS
     enough
    0.07
    .prototype
    0.07
     Institutions
    0.07
    Ӈ
    0.06
    .Fetch
    0.06
     şek
    0.06
     poop
    0.06
     ones
    0.06
    ❮
    0.06
    ää
    0.06
    Activations Density 0.015%

    No Known Activations