© 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. 41934
    Prev
    Next
    INDEX
    Explanations

    want something to

    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
    ÙĪاب
    -0.07
    åħ¨åĬĽæĶ¯æĮģ
    -0.07
    鼷æĸ¯
    -0.07
    oling
    -0.07
    主æĦı
    -0.07
     báºŃc
    -0.07
    Clone
    -0.07
    çļĦç»ĦåIJĪ
    -0.07
     isize
    -0.07
    åģıçĪ±
    -0.06
    POSITIVE LOGITS
     Phelps
    0.07
    ä»¿ä½Ľåľ¨
    0.07
    orex
    0.07
    minated
    0.07
    agine
    0.07
    udge
    0.07
    aptor
    0.06
    lian
    0.06
     thông
    0.06
    heu
    0.06
    Activations Density 0.025%

    No Known Activations