© 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. 34935
    Prev
    Next
    INDEX
    Explanations

    physical descriptors

    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
    èĻĶ
    -0.07
    opan
    -0.07
    -generic
    -0.07
    adeira
    -0.07
    çº
    -0.06
    åIJĮ声
    -0.06
    vaard
    -0.06
    itness
    -0.06
    äºĶæĺŁ
    -0.06
    ζί
    -0.06
    POSITIVE LOGITS
     внизÑĥ
    0.13
    åľ¨æ¯ı个
    0.12
    åľ¨åIJĦ个
    0.12
    åĪĨå¸ĥäºİ
    0.12
     everywhere
    0.12
     partout
    0.11
     ợ
    0.10
    两侧
    0.10
     vorne
    0.10
    æĹłè®ºæĺ¯åľ¨
    0.10
    Activations Density 0.545%

    No Known Activations