© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    National Forest, Haskell web, Japanese animation, Jamaica Premier

    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
    thic
    -0.08
    J
    -0.06
    ibold
    -0.06
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.06
    dat
    -0.06
    CT
    -0.06
     оп
    -0.06
    t
    -0.06
    dej
    -0.06
    riv
    -0.06
    POSITIVE LOGITS
    номо
    0.09
    ÙħÙĬÙĨ
    0.08
     Balai
    0.08
    oup
    0.08
    alang
    0.08
    foreground
    0.08
    ä¹İ
    0.08
    .dk
    0.08
    ecs
    0.07
    amani
    0.07
    Activations Density 2.086%

    No Known Activations