© 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. 34961
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and 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
    Negative Logits
    omot
    -0.08
    à´´
    -0.07
     lév
    -0.07
    edList
    -0.07
     Hopkins
    -0.07
    omo
    -0.07
    ooth
    -0.07
    éĺŁåľ¨
    -0.07
    离家
    -0.07
    å®Įåħ¨æ²¡æľī
    -0.07
    POSITIVE LOGITS
    udem
    0.07
     valid
    0.07
    bare
    0.07
    _stub
    0.07
    еÑģÑģи
    0.06
    olars
    0.06
    zano
    0.06
    _RD
    0.06
     ÙħØ·ÙĦ
    0.06
    arda
    0.06
    Activations Density 0.026%

    No Known Activations