© 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. 829
    Prev
    Next
    INDEX
    Explanations

    explants, stocks, mould, body, spent

    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
    yal
    -0.08
    edor
    -0.08
    avent
    -0.08
    UNUSED
    -0.08
     sorti
    -0.08
     ìŀħìŀ¥
    -0.07
    .setdefault
    -0.07
    eret
    -0.07
    urlencode
    -0.07
     Gore
    -0.07
    POSITIVE LOGITS
     bại
    0.06
    °
    0.06
    ä¸įåĢ¦
    0.06
     scrub
    0.06
    被æĬĵ
    0.06
    客
    0.06
    ?-
    0.05
    inna
    0.05
    0.05
    omod
    0.05
    Activations Density 0.406%

    No Known Activations