© 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. 8676
    Prev
    Next
    INDEX
    Explanations

    given

    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
    èIJĿèİī
    -0.08
    odox
    -0.07
    uzz
    -0.07
    ljan
    -0.07
     compreh
    -0.07
    acap
    -0.07
    ä¿ĬæĿ°
    -0.07
    æľ¨æĸ¯
    -0.07
    æ³Ľ
    -0.06
    моÑģ
    -0.06
    POSITIVE LOGITS
    iliar
    0.08
    éIJĺ
    0.07
    letal
    0.07
    crete
    0.07
     Preg
    0.07
    kout
    0.07
    ä¸įæĸĻ
    0.07
    çĮ®èº«
    0.06
    æ·ij
    0.06
    agate
    0.06
    Activations Density 0.023%

    No Known Activations