© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29903
    Prev
    Next
    INDEX
    Explanations

    numbers and abstract concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æħİ
    -0.08
     realistically
    -0.08
    为åĩĨ
    -0.07
    æĮĩæľĽ
    -0.07
    溯
    -0.07
    ført
    -0.07
     adequately
    -0.07
    otov
    -0.07
    æĺİçģ«
    -0.07
     abrasive
    -0.07
    POSITIVE LOGITS
    å·§åIJĪ
    0.11
     related
    0.10
     significance
    0.08
    related
    0.08
    è¿Ļ个æķ°åŃĹ
    0.08
    æľī趣
    0.08
    å¥ĩå¦ĻçļĦ
    0.08
    æľī趣çļĦæĺ¯
    0.08
     Interesting
    0.08
     interesting
    0.08
    Activations Density 0.027%

    No Known Activations