© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11560
    Prev
    Next
    INDEX
    Explanations

    numbers after $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofer
    -0.10
    æĬĺä¸įæī£
    -0.10
    ÄIJT
    -0.10
    xcf
    -0.10
    uket
    -0.10
    ErrMsg
    -0.09
    #line
    -0.09
    ×ķ׳×Ķ
    -0.09
    kert
    -0.09
    å¥¢æľĽ
    -0.09
    POSITIVE LOGITS
    0.08
     st
    0.07
     m
    0.07
     d
    0.07
     p
    0.06
     sh
    0.06
     ste
    0.06
     r
    0.06
    (
    0.06
    ↵
    0.06
    Activations Density 0.685%

    No Known Activations