© 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. 51949
    Prev
    Next
    INDEX
    Explanations

    formal/technical descriptions

    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
    ","+
    -0.08
    çĥ½
    -0.08
    ÙģÙĪر
    -0.08
    AuthProvider
    -0.08
    ĥģ
    -0.08
    pager
    -0.08
    apak
    -0.07
    igans
    -0.07
    æī¾åĪ°èĩªå·±
    -0.07
    转载æĪĸ
    -0.07
    POSITIVE LOGITS
    ç«ĭæĦı
    0.07
    gow
    0.07
    cue
    0.07
    åIJįæĢĿ
    0.07
    -outline
    0.07
    ics
    0.06
    ä¸Ģæĸij
    0.06
    æĪIJè´¥
    0.06
    ucz
    0.06
    urt
    0.06
    Activations Density 0.003%

    No Known Activations