© 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. 40144
    Prev
    Next
    INDEX
    Explanations

    technical keywords

    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
    oins
    -0.08
    ustry
    -0.08
    ÑģÑĮ
    -0.07
    ãģĹãģıãģ¯
    -0.07
    ок
    -0.07
    ////////////////////////////////////////////////////////////////////////////
    -0.07
    äºĭåįĬåĬŁåĢį
    -0.07
    ä¸Ģ个æĸ°çļĦ
    -0.07
    ipl
    -0.07
    åħ¶åIJį
    -0.06
    POSITIVE LOGITS
    èĩªå·±
    0.17
    adays
    0.15
    èĩªå·±æ²¡æľī
    0.14
    odore
    0.13
    etheless
    0.12
    èĩªå·±è¢«
    0.12
    quoi
    0.11
    ostante
    0.10
    gether
    0.09
    INCT
    0.09
    Activations Density 0.011%

    No Known Activations