© 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. 51879
    Prev
    Next
    INDEX
    Explanations

    lists of items, names, or code snippets

    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
    oref
    -0.07
    emas
    -0.07
    ë°ķ
    -0.07
     Tern
    -0.06
    rell
    -0.06
     Offen
    -0.06
    ioc
    -0.06
    uar
    -0.06
    vens
    -0.06
    åºIJ
    -0.06
    POSITIVE LOGITS
    è¿ĺæľī
    0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.08
    è¿ĺæľīå°±æĺ¯
    0.08
    éĤĦæľī
    0.08
    顾åIJįæĢĿ
    0.08
     etc
    0.07
    被åĪĹåħ¥
    0.07
    listed
    0.07
    人åIJį
    0.07
    ÑĢÑĤо
    0.07
    Activations Density 0.028%

    No Known Activations