© 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. 55500
    Prev
    Next
    INDEX
    Explanations

    can or we

    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
    èĩªè¡ĮæıIJä¾Ľ
    -0.08
    è¿ĻäºĽè¯Ŀ
    -0.08
    èĩªå·±
    -0.08
    èĩªå·±è¢«
    -0.08
    leven
    -0.08
    stitution
    -0.08
    resents
    -0.08
    thus
    -0.08
    ÙĪÙĨÙĩ
    -0.08
    struments
    -0.08
    POSITIVE LOGITS
    ully
    0.07
    fore
    0.07
    dating
    0.07
    atici
    0.07
    ↵↵
    0.07
    irem
    0.07
    ogg
    0.06
    fy
    0.06
    ä¸įåħ¨
    0.06
    I
    0.06
    Activations Density 0.002%

    No Known Activations