© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4613
    Prev
    Next
    INDEX
    Explanations

    four-dimensional

    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
    ingas
    -0.08
    quo
    -0.08
    fonds
    -0.08
    å¤ĸåĽ½è¯ŃåŃ¦æł¡
    -0.08
    æĿ
    -0.08
    祸é¦ĸ
    -0.08
    inato
    -0.08
    ograph
    -0.08
    tings
    -0.07
    æĺ¯ä¸Ģ家éĽĨ
    -0.07
    POSITIVE LOGITS
    ambu
    0.09
    rest
    0.07
    zzle
    0.07
    amer
    0.06
    วà¹Į
    0.06
    ishi
    0.06
    erce
    0.06
    à¹īà¸Ńà¸Ļ
    0.06
    uli
    0.06
    ace
    0.06
    Activations Density 0.001%

    No Known Activations