© 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. 64703
    Prev
    Next
    INDEX
    Explanations

    numerical values

    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
    èIJ½èIJ½
    -0.10
    à¸Ńยà¹Īาà¸ĩà¸Ķี
    -0.08
    mér
    -0.08
    ë°¥
    -0.07
    icky
    -0.07
    马æĭī
    -0.07
    iin
    -0.07
    ç»ĩ
    -0.07
    schirm
    -0.07
    schau
    -0.07
    POSITIVE LOGITS
    ont
    0.08
    ahas
    0.08
    vert
    0.07
    onti
    0.06
    ÙĪرÙī
    0.06
    ehr
    0.06
    渡åģĩ
    0.06
    eden
    0.06
    è¿ĺ羣çļĦ
    0.06
    ä¸ĩåı¤
    0.06
    Activations Density 0.011%

    No Known Activations