© 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. 64432
    Prev
    Next
    INDEX
    Explanations

    code completion and programming terms

    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
    mir
    -0.07
     Pati
    -0.06
    ç¿Ķ
    -0.06
     mir
    -0.06
    æľīæĿ¡ä»¶
    -0.06
     roub
    -0.06
    ç¥ĸ
    -0.06
    æĢĴæĶ¾
    -0.06
     Caval
    -0.06
    ICE
    -0.06
    POSITIVE LOGITS
    .yahoo
    0.09
    æīĢä½ľ
    0.08
    ystems
    0.08
    æ¯ıæĿ¡
    0.08
     intersect
    0.08
    横线
    0.08
    äºĨä¸ĢæĿ¡
    0.07
    åħ±äº§
    0.07
    ABCDE
    0.07
    침
    0.07
    Activations Density 0.002%

    No Known Activations