© 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. 51880
    Prev
    Next
    INDEX
    Explanations

    all but

    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
    ت
    -0.08
    ified
    -0.08
    ation
    -0.08
    ÙĬØ©
    -0.07
    Ø´
    -0.07
    м
    -0.07
    bilder
    -0.07
    an
    -0.07
    ±
    -0.07
    le
    -0.07
    POSITIVE LOGITS
    æľĢå¿«çļĦéĢŁåº¦
    0.13
    Ù°
    0.10
    èī²åĪĹ
    0.10
    人æ°ij为ä¸Ńå¿ĥ
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.09
    enticate
    0.08
    äººä¸ºæľ¬
    0.08
    etim
    0.08
    IELD
    0.08
    èĩ³æĸ¼
    0.08
    Activations Density 0.016%

    No Known Activations