© 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. 41438
    Prev
    Next
    INDEX
    Explanations

    integrate or function 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
     supers
    -0.06
    éĿ¢å¯¹
    -0.06
    åĽ´ç»ķçĿĢ
    -0.06
    quil
    -0.06
    æĿ¥æĬĵ
    -0.06
    èŀįåħ¥åĪ°
    -0.06
    <'
    -0.06
    anking
    -0.06
    åħīæĺ¯
    -0.06
    ä¸įè¿ĩæĿ¥
    -0.06
    POSITIVE LOGITS
    æīĢå±ŀåĪĨç±»
    0.08
    รà¹Į
    0.07
     Pris
    0.07
     trá»ħ
    0.07
    redd
    0.07
    esses
    0.07
    xef
    0.07
    arend
    0.07
    �t
    0.06
    ambul
    0.06
    Activations Density 0.085%

    No Known Activations