© 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. 45766
    Prev
    Next
    INDEX
    Explanations

    newly followed by participle

    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
    emente
    -0.10
    缸è¾ħ缸æĪIJ
    -0.10
    issement
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    åľ¨åIJij
    -0.09
    æĸ°åĬłåĿ¡
    -0.09
    ingin
    -0.08
    ipel
    -0.08
    gence
    -0.08
    avig
    -0.08
    POSITIVE LOGITS
    æĮĩçļĦ
    0.08
    åŃļ
    0.08
    èĩ´çļĦ
    0.08
    çŁ¥çļĦ
    0.08
    æ±Ĥæĺ¯
    0.07
    iw
    0.07
    elian
    0.07
    ppard
    0.07
    ippy
    0.07
    ار
    0.06
    Activations Density 0.017%

    No Known Activations