© 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. 23736
    Prev
    Next
    INDEX
    Explanations

    simplify, shorten, terminology

    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
    logs
    -0.07
    éĤ®
    -0.07
    halb
    -0.07
    延
    -0.07
    æľīä¸Ģä½į
    -0.07
    ak
    -0.06
    acre
    -0.06
     realistically
    -0.06
    oeff
    -0.06
    ovu
    -0.06
    POSITIVE LOGITS
     format
    0.08
    ä¸ŃæıIJåıĸ
    0.07
    ä¸įæį¢
    0.07
    æł¼å¼ı
    0.07
    antro
    0.07
    lä
    0.07
    æĶ¯ä»ĺæĸ¹å¼ı
    0.07
    æĻļæĬ¥
    0.07
    ixer
    0.07
    abay
    0.07
    Activations Density 0.001%

    No Known Activations