© 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. 37598
    Prev
    Next
    INDEX
    Explanations

    url, string manipulation

    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
    eworld
    -0.08
    ¶
    -0.07
    SELL
    -0.07
     SOB
    -0.07
     eng
    -0.07
     doty
    -0.07
    arness
    -0.07
    akin
    -0.07
    妨
    -0.07
    ibir
    -0.06
    POSITIVE LOGITS
    lew
    0.08
    ugas
    0.07
    .pi
    0.07
    çİ®
    0.07
    uyo
    0.06
    äºİä»Ĭå¹´
    0.06
    ìĶ¨
    0.06
    ÛĮات
    0.06
    æī¦
    0.06
    edig
    0.06
    Activations Density 0.015%

    No Known Activations