© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44725
    Prev
    Next
    INDEX
    Explanations

    ECT email addresses

    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
    Negative Logits
    oghi
    -0.07
    å§Ķåijĺä¼ļ主任
    -0.07
    reeze
    -0.07
    (nb
    -0.06
    stm
    -0.06
    chemes
    -0.06
    xt
    -0.06
     Nos
    -0.06
    gow
    -0.06
    太ä»ĵ
    -0.06
    POSITIVE LOGITS
    Tal
    0.07
    .wik
    0.06
    icitÃł
    0.06
    iania
    0.06
    yant
    0.06
    HTTPRequest
    0.06
     vet
    0.06
     shuts
    0.06
    æĭIJæĿĸ
    0.06
    licity
    0.06
    Activations Density 0.213%

    No Known Activations