© 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. 34918
    Prev
    Next
    INDEX
    Explanations

    colors or letters followed by punctuation

    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
    å½ĵ家
    -0.07
    /out
    -0.07
    磨
    -0.06
    ä¸ĢäºĽçļĦ
    -0.06
    mont
    -0.06
    éĥ½æĹłæ³ķ
    -0.06
    ulos
    -0.06
    ion
    -0.06
    =}
    -0.06
    κοÏħ
    -0.06
    POSITIVE LOGITS
    åŃ
    0.07
    omic
    0.07
    su
    0.07
    илÑĮ
    0.06
    oya
    0.06
    ogg
    0.06
    ä¸įèĭŁ
    0.06
    åİŁåĪĽæĸĩç«ł
    0.06
    _magic
    0.06
    atable
    0.06
    Activations Density 0.003%

    No Known Activations