© 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. 55229
    Prev
    Next
    INDEX
    Explanations

    Diana Cavallaro

    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
    ä¸īåIJį
    -0.07
    ä¸ī个éĺ¶æ®µ
    -0.07
    ä¸ī大
    -0.07
    åİŁåIJį
    -0.07
    cn
    -0.07
    ä¸ī个åŃĹ
    -0.07
    three
    -0.07
    oca
    -0.07
     three
    -0.07
    çļĦä¸ī个
    -0.07
    POSITIVE LOGITS
    åģ¥
    0.07
     eve
    0.07
    注
    0.07
    mund
    0.07
    çĿ¹
    0.07
     jo
    0.07
    anne
    0.07
    _ctl
    0.07
    èĥ
    0.07
     Gaw
    0.07
    Activations Density 0.209%

    No Known Activations