© 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. 40525
    Prev
    Next
    INDEX
    Explanations

    removing parts or sections

    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
    ç©¿éĢı
    -0.08
     Spread
    -0.08
    -await
    -0.08
    arness
    -0.08
    å¸ĥæŀĹ
    -0.07
    spread
    -0.07
    æĬĬæīĢæľīçļĦ
    -0.07
    Spread
    -0.07
    ä¸ŃæĸĩåIJį
    -0.07
    DOMContentLoaded
    -0.07
    POSITIVE LOGITS
     portions
    0.12
     fragment
    0.12
    åĪĩéĻ¤
    0.12
     portion
    0.11
     fragments
    0.11
    åĪĩéĻ¤æľ¯
    0.11
    çīĩ段
    0.11
    .fragment
    0.11
    缺失
    0.10
    ä¸ĢåĿĹ
    0.10
    Activations Density 0.215%

    No Known Activations