© 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. 18704
    Prev
    Next
    INDEX
    Explanations

    usual suspects

    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
    èĩªçĦ¶èĢĮ
    -0.07
    ÑĤан
    -0.07
    ait
    -0.07
    etro
    -0.06
    regen
    -0.06
    umberland
    -0.06
    alum
    -0.06
    è¿ĺ羣
    -0.06
    adan
    -0.06
    кÑĢовен
    -0.06
    POSITIVE LOGITS
    ล
    0.08
    å±ķå¼Ģåħ¨æĸĩ
    0.08
    viel
    0.07
    ä¼łç»ŁçļĦ
    0.07
     ìĿµ
    0.07
     thing
    0.07
    æĹħæ¸¸çĽ®çļĦåľ°
    0.07
     usual
    0.07
    <![
    0.07
    ç»ıåħ¸çļĦ
    0.07
    Activations Density 0.267%

    No Known Activations