© 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. 34734
    Prev
    Next
    INDEX
    Explanations

    commonly used or keeping up to date

    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
    laf
    -0.06
    UP
    -0.06
    æŶåĪĨ
    -0.06
    itech
    -0.06
    Wiki
    -0.06
    åĨ³å®ļ
    -0.06
    åĨ³å®ļäºĨ
    -0.06
    .alibaba
    -0.06
    åħĭåĬĽ
    -0.06
    stein
    -0.06
    POSITIVE LOGITS
    ient
    0.07
    æĸĩåĵ²
    0.07
    orent
    0.07
    _BLE
    0.07
    ifo
    0.07
    /or
    0.07
    ftime
    0.07
    æķĻèĤ²éĽĨåĽ¢
    0.07
    abbo
    0.07
    assing
    0.07
    Activations Density 0.067%

    No Known Activations