© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39813
    Prev
    Next
    INDEX
    Explanations

    mathematical notation punctuation

    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
    èĩªå·±
    -0.13
    èĩªå·±æ²¡æľī
    -0.11
    èĩªå·±è¢«
    -0.11
    ../../../
    -0.10
    quoi
    -0.09
    efois
    -0.09
    bsites
    -0.09
    ะ
    -0.08
    ÑģÑı
    -0.08
    gether
    -0.08
    POSITIVE LOGITS
    apsed
    0.09
    yce
    0.07
    дели
    0.07
    emento
    0.07
    ained
    0.07
    iors
    0.07
     ($('#
    0.06
    avior
    0.06
    Åijs
    0.06
    0.06
    Activations Density 0.015%

    No Known Activations