© 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. 47234
    Prev
    Next
    INDEX
    Explanations

    be to the

    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
    uluh
    -0.07
    _icall
    -0.07
    åľ°åĿĢä½įäºİ
    -0.07
     ÃĤn
    -0.07
    åİŁåĪĽæĸĩç«ł
    -0.07
     omas
    -0.07
    (Expected
    -0.07
    வà¯ĩ
    -0.06
    ×ķ×ij×Ķ
    -0.06
    ÂŃi
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮäºĨ
    0.07
    å¤ļ好
    0.07
    å°Ķå¾·
    0.07
    azine
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.07
    λει
    0.07
    hausen
    0.06
    usher
    0.06
    æĹłæ¯ĶçļĦ
    0.06
    æĹłæŃ¢å¢ĥ
    0.06
    Activations Density 0.034%

    No Known Activations