© 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. 4189
    Prev
    Next
    INDEX
    Explanations

    languages and regular expressions

    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
    aeda
    -0.07
    éĴĿ
    -0.07
    éªĭ
    -0.06
    è¿Ļç§įåģļæ³ķ
    -0.06
    -mort
    -0.06
    é³Į
    -0.06
    çļ®çIJĥ
    -0.06
    å½ĵåľ°æŶéĹ´
    -0.06
     gle
    -0.06
    é¸ŃèĽĭ
    -0.06
    POSITIVE LOGITS
     luá»ĵng
    0.09
     substring
    0.08
     RegExp
    0.08
    utter
    0.08
     synt
    0.08
    Regex
    0.08
     alphabet
    0.07
    åIJŀåIJIJ
    0.07
     concaten
    0.07
     infix
    0.07
    Activations Density 0.017%

    No Known Activations