© 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. 13247
    Prev
    Next
    INDEX
    Explanations

    geometric and mathematical terms

    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
    antang
    -0.08
    综åIJĪæĢ§
    -0.08
     encodeURIComponent
    -0.08
    æĹłè®ºä»İ
    -0.07
     Bent
    -0.07
    _DECLARE
    -0.07
    istrar
    -0.07
     Channel
    -0.07
    转贴
    -0.07
    踢
    -0.07
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.08
     voire
    0.08
     rather
    0.08
    èĢĮä¸įæĺ¯
    0.07
     thôi
    0.07
    Sk
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    ä½Ĩä¸į
    0.07
    æľªå¿ħ
    0.07
    øn
    0.07
    Activations Density 0.015%

    No Known Activations