© 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. 25823
    Prev
    Next
    INDEX
    Explanations

    $ and * markers

    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
    ugged
    -0.08
    ugging
    -0.08
    onest
    -0.08
    Indented
    -0.08
    assen
    -0.07
    udel
    -0.07
     hopefully
    -0.07
    anou
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    ennifer
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.07
    åħīæĺ¯
    0.07
     Effect
    0.06
    że
    0.06
    ï¸ı
    0.06
    å¾Ĭ
    0.06
     only
    0.06
    ιε
    0.06
    åĦ¿
    0.06
    æĺ¯æ²¡æľī
    0.06
    Activations Density 0.009%

    No Known Activations