© 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. 44356
    Prev
    Next
    INDEX
    Explanations

    calculation or intermediate

    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
    éħįç½®æĸ¹éĿ¢
    -0.07
    éĿ¢åIJij社ä¼ļ
    -0.07
     envelop
    -0.07
    athing
    -0.07
    .removeAll
    -0.07
    OMO
    -0.07
    nings
    -0.07
    zny
    -0.07
    лама
    -0.07
    è®©æĽ´å¤ļ
    -0.07
    POSITIVE LOGITS
     calculation
    0.07
    å¸ĸ
    0.07
     Calculation
    0.07
    ypo
    0.07
    åķĨ
    0.07
    ghi
    0.07
     intermediate
    0.07
    å¼Ĥ彩
    0.07
    itty
    0.07
    asion
    0.06
    Activations Density 0.004%

    No Known Activations