© 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. 32580
    Prev
    Next
    INDEX
    Explanations

    word followed by number or token

    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
    å¢Ł
    -0.07
    夷
    -0.07
    mie
    -0.07
    æݨéĶĢ
    -0.07
    ãĤ°ãĥ¬
    -0.07
    æĽ´åIJį
    -0.07
    æ¯ķä¸ļçĶŁçļĦ
    -0.07
     vist
    -0.07
    æĹłäºĭ
    -0.06
     بØŃÙĬ
    -0.06
    POSITIVE LOGITS
    ä¸įä»ħåı¯ä»¥
    0.06
    å¿ħ
    0.06
    ubl
    0.06
    æĭīå¼Ģ
    0.06
    pn
    0.06
    èį¡
    0.06
    eb
    0.06
    بÙĪÙĦ
    0.06
    ä¸įä»ħèĥ½
    0.06
    PUR
    0.06
    Activations Density 0.018%

    No Known Activations