© 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. 62271
    Prev
    Next
    INDEX
    Explanations

    division and `)`

    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
    赤
    -0.08
    ạc
    -0.07
    ltk
    -0.07
    ÑĢно
    -0.07
    ç¡
    -0.07
    UH
    -0.07
    artz
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    _ALLOC
    -0.07
    abat
    -0.07
    POSITIVE LOGITS
    invert
    0.09
     invert
    0.09
     inverse
    0.08
    inverse
    0.07
    Inverse
    0.07
    æıIJé«ĺèĩªå·±çļĦ
    0.07
     invers
    0.07
    äºĴ为
    0.07
    maal
    0.07
    è©°
    0.07
    Activations Density 0.008%

    No Known Activations