© 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. 51885
    Prev
    Next
    INDEX
    Explanations

    code class definitions

    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
    èĨĬ
    -0.07
    åı¯è§Ĥ
    -0.07
    atorie
    -0.06
    ëł
    -0.06
    æī©å¼ł
    -0.06
    odik
    -0.06
    yt
    -0.06
    .cp
    -0.06
    rá
    -0.06
    thead
    -0.06
    POSITIVE LOGITS
    sWith
    0.10
    -runner
    0.08
    readcrumbs
    0.07
    çĿ
    0.07
    åıĬéħįå¥Ĺ
    0.07
    -wrapper
    0.07
    onders
    0.07
    urez
    0.07
     maga
    0.07
    meeting
    0.07
    Activations Density 0.006%

    No Known Activations