© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25080
    Prev
    Next
    INDEX
    Explanations

    specific instances of things

    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
    chemes
    -0.07
    æ²»
    -0.06
    è¿Ļç§įä¸ľè¥¿
    -0.06
    ç»Ħç»ĩèĢħ
    -0.06
     nhau
    -0.06
     infinit
    -0.06
    åľ¨æ¯ı个
    -0.06
     Separate
    -0.06
    ew
    -0.06
    dor
    -0.06
    POSITIVE LOGITS
    ĮĢ
    0.08
    åIJĦæĸ¹éĿ¢
    0.08
    æĬĢæľ¯åıĤæķ°
    0.08
    çĻ»å½ķæŁ¥çľĭ
    0.08
    iant
    0.08
     described
    0.08
     modest
    0.08
    详ç»Ĩä¿¡æģ¯
    0.07
    å¹´å¤ļ
    0.07
     ÑħаÑĢакÑĤеÑĢиÑģÑĤики
    0.07
    Activations Density 0.040%

    No Known Activations