© 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. 7269
    Prev
    Next
    INDEX
    Explanations

    sequence elements

    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
    她说
    -0.07
    ä»ĸ说
    -0.07
    为éĩįçĤ¹
    -0.07
    ude
    -0.07
     lÃŃt
    -0.07
    宽çļĦ
    -0.06
    è¿ĺ好
    -0.06
    nowrap
    -0.06
    éŃħ
    -0.06
    èı±
    -0.06
    POSITIVE LOGITS
    ocol
    0.07
    icura
    0.07
     NOTA
    0.07
    editable
    0.07
    nehmen
    0.07
    cmc
    0.06
     /**<
    0.06
    thur
    0.06
     Ahead
    0.06
    thead
    0.06
    Activations Density 0.024%

    No Known Activations