© 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. 41487
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    esian
    -0.08
    intl
    -0.08
    dle
    -0.08
    ç½ij绾æݨ广
    -0.08
    inux
    -0.08
    iy
    -0.07
    vrier
    -0.07
    èīº
    -0.07
    ugin
    -0.07
    æºĸ
    -0.07
    POSITIVE LOGITS
    apak
    0.07
    以èĩªå·±
    0.07
    boxed
    0.07
    ankan
    0.06
     REPL
    0.06
    agas
    0.06
    ç§įç§įåİŁåĽł
    0.06
    è¡·
    0.06
    æĪijåIJ§
    0.06
     ë§Į
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.