© 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. 28155
    Prev
    Next
    INDEX
    Explanations

    colon followed by text

    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
    stig
    -0.07
    æ³ķå¾ĭè§Ħå®ļ
    -0.07
    odr
    -0.07
    éļĻ
    -0.06
    pong
    -0.06
    ç²ī
    -0.06
    è¿Ļä¸ĢåĪ»
    -0.06
    ä¸ŃåĽ½
    -0.06
    æł¼
    -0.06
    ps
    -0.06
    POSITIVE LOGITS
    tul
    0.09
    vern
    0.08
    kul
    0.08
    è¿Ħ
    0.08
    iful
    0.08
    illy
    0.07
    oard
    0.07
    æľĪåºķåīį
    0.07
    apper
    0.07
    पà¥Ĥरà¥į
    0.07
    Activations Density 0.001%

    No Known Activations