© 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. 52154
    Prev
    Next
    INDEX
    Explanations

    unit or uniform distribution / starts with u

    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
     иÑģкÑĥÑģÑģÑĤв
    -0.07
    ä¸įæ¸Ŀ
    -0.07
    rix
    -0.07
    æĹıèĩªæ²»å·ŀ
    -0.06
    AndUpdate
    -0.06
    OrUpdate
    -0.06
    ché
    -0.06
     lẻ
    -0.06
    zcz
    -0.06
    -quarters
    -0.06
    POSITIVE LOGITS
    ÑĤÑĢеннÑıÑı
    0.13
    /down
    0.13
    psilon
    0.12
    Ñģловно
    0.11
    нÑĸвеÑĢ
    0.11
    ltra
    0.10
    kraine
    0.09
    ÑģÑĮого
    0.09
    ubat
    0.09
    ilater
    0.09
    Activations Density 0.421%

    No Known Activations