© 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. 35030
    Prev
    Next
    INDEX
    Explanations

    powers of 2

    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
    etto
    -0.07
    æį·
    -0.07
    åĦ¿çļĦ
    -0.07
    FromArray
    -0.07
    eis
    -0.07
    agrid
    -0.06
    è·Łè´´
    -0.06
    jsc
    -0.06
    à¥įà¤ŀ
    -0.06
    faat
    -0.06
    POSITIVE LOGITS
     izb
    0.07
    ritz
    0.07
    bole
    0.06
    ukk
    0.06
    erior
    0.06
    izin
    0.06
    hy
    0.06
    hui
    0.06
    rib
    0.06
    iza
    0.06
    Activations Density 0.002%

    No Known Activations