© 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. 55117
    Prev
    Next
    INDEX
    Explanations

    numbers and units or years

    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
    ä¾Ŀæ³ķèĩªä¸»
    -0.07
    ess
    -0.06
    ç½ijç«Ļåľ°åĽ¾
    -0.06
    ={$
    -0.06
    -related
    -0.06
    P
    -0.06
    ìļ¸
    -0.06
    GI
    -0.06
    man
    -0.06
     Plain
    -0.06
    POSITIVE LOGITS
    åħ¬åı¸æĸ°éĹ»
    0.09
    ucht
    0.08
    uche
    0.07
    öll
    0.07
    UIL
    0.07
    оÑĤи
    0.07
    ISTI
    0.07
    idon
    0.07
    ksen
    0.07
    åįĥéĩĮ
    0.07
    Activations Density 0.009%

    No Known Activations