© 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. 20189
    Prev
    Next
    INDEX
    Explanations

    import os, glm, standard library usage

    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
    bung
    -0.08
    æľīæĪIJæķĪ
    -0.08
    LEAN
    -0.07
    uvia
    -0.07
    Ả
    -0.07
    dra
    -0.07
    æݨèįIJç»Ļ
    -0.07
    æĮ¯åįİ
    -0.07
    ameleon
    -0.07
    virtual
    -0.07
    POSITIVE LOGITS
    /by
    0.07
    ново
    0.06
    eder
    0.06
    è¿ĻæĬĬ
    0.06
    BY
    0.06
     l
    0.06
    abby
    0.06
    éĹ¨æ´¾
    0.06
    å¿į
    0.06
    æĹħ
    0.06
    Activations Density 0.124%

    No Known Activations