© 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. 23945
    Prev
    Next
    INDEX
    Explanations

    version specifiers and numbers

    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
    olicy
    -0.09
    éĶ¦æ¶Ľ
    -0.08
    .createClass
    -0.07
    ÙĨاد
    -0.07
    ç§ijæĬĢåѦéĻ¢
    -0.07
    Ĩµ
    -0.07
    丽åįİ
    -0.07
    trup
    -0.07
    umin
    -0.07
    arent
    -0.07
    POSITIVE LOGITS
     коллеги
    0.07
    å°±åľ¨è¿Ļ
    0.07
    ä¸īéĥ¨
    0.07
    anford
    0.06
    _dependencies
    0.06
    stable
    0.06
    Owned
    0.06
    வà¯ĩ
    0.06
    ki
    0.06
     vX
    0.06
    Activations Density 0.004%

    No Known Activations