© 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. 7121
    Prev
    Next
    INDEX
    Explanations

    .php extension

    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
    §
    -0.08
    enu
    -0.07
    illon
    -0.07
    èĢĮä»ĸçļĦ
    -0.06
    ¬
    -0.06
    ī
    -0.06
    aggi
    -0.06
    _picker
    -0.06
    ftware
    -0.06
    ¢
    -0.06
    POSITIVE LOGITS
    两个åŃĹ
    0.07
    äºijå³°
    0.07
    çļĦåij¢
    0.06
    ãģ®ãĤĤãģ®
    0.06
    æľīåIJį
    0.06
    cÄĥ
    0.06
    Contours
    0.06
    รัมยà¹Į
    0.06
    bay
    0.06
    beth
    0.06
    Activations Density 0.017%

    No Known Activations