© 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. 24441
    Prev
    Next
    INDEX
    Explanations

    unit/units

    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
    anio
    -0.08
    oplayer
    -0.08
    ader
    -0.07
    ç¨ĭ度ä¸Ĭ
    -0.07
    oad
    -0.07
    ponent
    -0.07
    _INCLUDED
    -0.07
    éĥ¨åĪĨç»ĦæĪIJ
    -0.07
    产åĵģåı¬åĽŀ
    -0.07
     Luck
    -0.07
    POSITIVE LOGITS
    less
    0.09
    -less
    0.09
    apa
    0.08
    ìŀIJìľł
    0.07
    ±
    0.07
    转æį¢
    0.07
    igos
    0.07
    å§Ķåijĺä¼ļ主任
    0.07
    ink
    0.07
    åĴĮåĨħ容
    0.06
    Activations Density 0.004%

    No Known Activations