© 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. 8782
    Prev
    Next
    INDEX
    Explanations

    Montenegro v

    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
    estens
    -0.07
    alach
    -0.07
    åīĽ
    -0.07
    åĿŀ
    -0.06
    ç»Ĵ
    -0.06
    妮
    -0.06
    åĪļ
    -0.06
    allee
    -0.06
    лем
    -0.06
    uest
    -0.06
    POSITIVE LOGITS
    ÏĢÎŃ
    0.08
    æĪĸ被
    0.07
    ä¸įéľĢ
    0.07
    cout
    0.07
    rotch
    0.07
    //{{
    0.07
    chaft
    0.07
    ä¸Ĭè·¯
    0.07
    biz
    0.07
    ä¸įè¯Ń
    0.07
    Activations Density 0.028%

    No Known Activations