© 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. 24330
    Prev
    Next
    INDEX
    Explanations

    mean +/-

    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
    rup
    -0.06
     dipped
    -0.06
    amai
    -0.06
     Accept
    -0.06
     Dip
    -0.06
    她éĥ½
    -0.06
    ambo
    -0.06
    /
    -0.06
     ê±´
    -0.06
    åįķä¸ĢçļĦ
    -0.06
    POSITIVE LOGITS
    nez
    0.09
    षà¥įà¤ł
    0.08
    ıŁ
    0.08
    ª½
    0.08
    avage
    0.08
     diza
    0.08
    ayu
    0.08
    teis
    0.08
    chè
    0.08
    зан
    0.08
    Activations Density 0.042%

    No Known Activations