© 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. 7928
    Prev
    Next
    INDEX
    Explanations

    from negative to positive

    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
    WithPath
    -0.07
    ä½Ĩä¸İ
    -0.07
    ullets
    -0.07
    åħ¨åĭ¤
    -0.07
    ä¸İä¼łç»Ł
    -0.07
    archs
    -0.07
    ä¸İèĩªå·±
    -0.07
    -slider
    -0.07
     Fortune
    -0.07
     Carlson
    -0.07
    POSITIVE LOGITS
    —from
    0.08
    åħ®
    0.08
    teau
    0.08
    æ·±åħ¥æµħ
    0.08
    ingly
    0.07
    LEC
    0.07
    itivo
    0.06
    aschen
    0.06
    ä¸įå°±
    0.06
    ilden
    0.06
    Activations Density 0.008%

    No Known Activations