© 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. 44756
    Prev
    Next
    INDEX
    Explanations

    son of

    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
    enne
    -0.07
    ----
    -0.07
    æį®
    -0.07
    akar
    -0.07
    åIJĦæĹı
    -0.07
    à¹Īาà¸ĩ
    -0.07
    书
    -0.07
    ics
    -0.06
    zil
    -0.06
    !--
    -0.06
    POSITIVE LOGITS
    stvÃŃ
    0.08
    ëłģ
    0.08
    xFFFFFF
    0.07
    ä¸į误
    0.07
    xffffff
    0.07
    riqu
    0.07
    åIJĥèĭ¦
    0.07
    strup
    0.07
    uxt
    0.06
    xFFFF
    0.06
    Activations Density 0.276%

    No Known Activations