© 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. 55467
    Prev
    Next
    INDEX
    Explanations

    numbers and words of titles

    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
    çļĦåIJĦç§į
    -0.07
    ä¸įåħī
    -0.07
    çīĮçħ§
    -0.07
    æĮĩå®ļçļĦ
    -0.07
    amped
    -0.07
     âĦķ
    -0.07
    ä¸įæŃ¢
    -0.07
    Ñĥз
    -0.07
    âĢİ
    -0.06
    æīĢæĢĿ
    -0.06
    POSITIVE LOGITS
    ä¸İ伦
    0.07
    irat
    0.07
    lei
    0.07
    ç¬ijåĤ²
    0.07
    è§Ĵ度æĿ¥çľĭ
    0.07
    æĪijä¸įè¦ģ
    0.07
    åľ¨è¿ĻéĩĮ
    0.06
    erbe
    0.06
    iedy
    0.06
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    0.06
    Activations Density 0.002%

    No Known Activations