© 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. 52205
    Prev
    Next
    INDEX
    Explanations

    zero values, placeholders

    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
    recht
    -0.07
    æĶ¿çŃĸæݪæĸ½
    -0.06
    erland
    -0.06
    ãģħ
    -0.06
    lique
    -0.06
    à¸ij
    -0.06
    ÑħÑĢан
    -0.06
    .opensource
    -0.06
    é¶
    -0.06
    å¡ĺéķĩ
    -0.06
    POSITIVE LOGITS
    olim
    0.08
    .wrap
    0.08
    å°»
    0.07
     NDEBUG
    0.07
    å¿ĥçļĦ
    0.07
    zyw
    0.07
    ãģĺ
    0.07
    å¿ĥ
    0.07
    ABCDEFG
    0.07
    ebol
    0.07
    Activations Density 0.251%

    No Known Activations