© 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. 57736
    Prev
    Next
    INDEX
    Explanations

    rate, rapid, scan

    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
    å±ħé«ĺ
    -0.07
    æīģ
    -0.07
    åįİåĽ¾
    -0.07
    ç¨³åĽº
    -0.07
    空缺
    -0.07
    空èĻļ
    -0.07
    æł¹æ·±
    -0.07
     Lesser
    -0.07
    æł¼åŃIJ
    -0.07
    å·©åĽº
    -0.07
    POSITIVE LOGITS
    è¿ĩå¿«
    0.11
     rapid
    0.11
    å¿«åĪ°
    0.11
    è¶Ĭå¿«
    0.11
    太快
    0.11
    rapid
    0.10
    æĢ¥ä¿ĥ
    0.10
    å¾Īå¿«çļĦ
    0.10
     ramp
    0.10
    éĢŁçİĩ
    0.09
    Activations Density 0.032%

    No Known Activations