© 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. 47383
    Prev
    Next
    INDEX
    Explanations

    approximate numbers and ranges

    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
    ourced
    -0.08
     probabil
    -0.08
    æĽ¾ç»ıçļĦ
    -0.07
    ä½Ĩæĺ¯çİ°åľ¨
    -0.07
    udre
    -0.07
    èĮ¹
    -0.07
    &C
    -0.07
    èĬĿ
    -0.07
     Ferd
    -0.07
    ØŃا
    -0.07
    POSITIVE LOGITS
     cloned
    0.07
    enis
    0.06
    Dict
    0.06
    finger
    0.06
    ante
    0.06
    æ´Ĺ
    0.06
    çĸ¯
    0.06
    åIJĮå·¥
    0.06
     lip
    0.06
    .templates
    0.06
    Activations Density 2.098%

    No Known Activations