© 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. 1650
    Prev
    Next
    INDEX
    Explanations

    unrefined food

    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
     ÙĨاÙģ
    -0.07
    _multiply
    -0.07
    ä¸įæĺĵ
    -0.07
    akt
    -0.07
    èĢĮéĿŀ
    -0.07
    ewa
    -0.07
     구ìĦ±
    -0.07
    ä¸į容æĺĵ
    -0.07
    天ä¸ĭ
    -0.06
     peu
    -0.06
    POSITIVE LOGITS
     anymore
    0.15
    æľīä»»ä½ķ
    0.13
    ä»»ä½ķ
    0.12
     whatsoever
    0.11
    ä»»ä½ķå½¢å¼ıçļĦ
    0.11
    æıIJä¾Ľä»»ä½ķ
    0.11
    ä»»ä½ķ人
    0.11
    æĽ´ä¸įèĥ½
    0.11
    ä»»ä½ķçļĦ
    0.11
     altogether
    0.11
    Activations Density 0.150%

    No Known Activations