© 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. 4675
    Prev
    Next
    INDEX
    Explanations

    although clauses

    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
    nip
    -0.08
    avers
    -0.08
    alytics
    -0.08
    ãĤĪãģĨãģ«ãģªãĤĭ
    -0.07
    azon
    -0.07
    edly
    -0.07
    ropolit
    -0.07
    èĢĮä»ĸçļĦ
    -0.07
    itionally
    -0.07
    elib
    -0.07
    POSITIVE LOGITS
    ç§įç§įåİŁåĽł
    0.15
    ÑģÑĮ
    0.11
    åIJĦç§įåİŁåĽł
    0.10
    er
    0.10
    о
    0.09
    erÃŃa
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    ly
    0.09
    ÑģÑı
    0.08
    лÑĮкÑĥ
    0.08
    Activations Density 0.015%

    No Known Activations