© 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. 15829
    Prev
    Next
    INDEX
    Explanations

    parameter documentation

    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
    ryn
    -0.08
    lø
    -0.08
    ocab
    -0.08
    ollo
    -0.08
    祸
    -0.08
     opro
    -0.07
    æīĢ以å½ĵ
    -0.07
    ç¢ī
    -0.07
    ãģĺãĤĵ
    -0.07
    гон
    -0.07
    POSITIVE LOGITS
    çĴŀ
    0.07
    [in
    0.07
     Param
    0.07
    æ¸
    0.07
    emente
    0.06
    itaire
    0.06
    åŃĺ
    0.06
    .param
    0.06
    è¾ĵåħ¥
    0.06
     VARIABLE
    0.06
    Activations Density 0.019%

    No Known Activations