© 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. 34946
    Prev
    Next
    INDEX
    Explanations

    image, raster, graphics

    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
     UIF
    -0.07
    _INCLUDED
    -0.07
    apé
    -0.07
    itest
    -0.07
    æĹ©çŁ¥éģĵ
    -0.07
    西æĸ¯
    -0.07
    å·²çŁ¥
    -0.07
    azar
    -0.07
    æĢ»æĦŁè§ī
    -0.07
    ä¹Ŀ寨
    -0.07
    POSITIVE LOGITS
    -cover
    0.07
    ajah
    0.07
    ç»Ń
    0.07
    ÅĻej
    0.07
    erra
    0.07
    è¿ĻåŃ¦æľŁ
    0.07
    åģļäºĭæĥħ
    0.07
    å¨ĥ
    0.06
    å¤Ħäºĭ
    0.06
     Haag
    0.06
    Activations Density 0.191%

    No Known Activations