© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    options followed by closing parenthesis

    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
    beck
    -0.09
    æ´Ľæĸ¯
    -0.08
    äºijé£ŀ
    -0.07
    æŶéĹ´åľ¨
    -0.07
    ãģµ
    -0.07
    èµ·å±ħ
    -0.07
    imen
    -0.07
    ilus
    -0.07
    /fr
    -0.07
    æľ¬èģĮ
    -0.07
    POSITIVE LOGITS
    å¥½å¥½åľ°
    0.08
     Unable
    0.07
    åįķéĢīé¢ĺ
    0.07
    alisation
    0.07
    arda
    0.06
    代
    0.06
    人éĢī
    0.06
    онеÑĢа
    0.06
    ardan
    0.06
    ÑĤки
    0.06
    Activations Density 0.009%

    No Known Activations