© 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. 44825
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    seh
    -0.07
    unjung
    -0.07
    olf
    -0.07
    es
    -0.06
    æľĿæ°Ķ
    -0.06
    kehr
    -0.06
    eger
    -0.06
    urt
    -0.06
    ei
    -0.06
    /or
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.12
    æµĴ
    0.08
    ypes
    0.08
    à¸Ľà¸±à¸ĩ
    0.08
    éĵ¶è¡ĮèĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.08
    ä¸Ģ项
    0.08
    еÑģÑĤвÑĥ
    0.08
     @}
    0.08
    uttle
    0.07
     erotici
    0.07
    Activations Density 0.004%

    No Known Activations