© 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. 4898
    Prev
    Next
    INDEX
    Explanations

    punctuation and word fragments

    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
    éné
    -0.08
    estu
    -0.06
     elettr
    -0.06
     elektrik
    -0.06
    çĶµè¯ĿåĴ¨è¯¢
    -0.06
    æ·±åıĹ广大
    -0.06
     Fool
    -0.06
    omy
    -0.06
     tender
    -0.06
    elek
    -0.06
    POSITIVE LOGITS
    sker
    0.10
    aih
    0.07
    sak
    0.07
    UTH
    0.07
    andia
    0.07
    ÑĦеÑĢ
    0.07
    ungg
    0.07
    owska
    0.07
    orda
    0.07
    ovin
    0.07
    Activations Density 0.437%

    No Known Activations