© 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. 27762
    Prev
    Next
    INDEX
    Explanations

    either 0 or 1

    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
    vang
    -0.07
    èį¡
    -0.07
    efore
    -0.07
    czyk
    -0.07
    veyor
    -0.07
    éģIJ
    -0.07
    éħ¸çĶľèĭ¦è¾£
    -0.07
    olver
    -0.07
    çīµè¿ŀ
    -0.07
     ÏĥÏħνÎŃ
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.09
    为主
    0.08
     depending
    0.08
     occasionally
    0.08
    两ç§į
    0.08
    Occurred
    0.08
     occasional
    0.08
     randomly
    0.08
    äº¤æĽ¿
    0.08
    æ··åIJĪ
    0.07
    Activations Density 0.049%

    No Known Activations