© 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. 16947
    Prev
    Next
    INDEX
    Explanations

    words after "studies" or "text"

    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
    æľīåı¯èĥ½æĺ¯
    -0.09
     Redistributions
    -0.09
    oser
    -0.08
    atatype
    -0.08
    _ENC
    -0.08
     ene
    -0.08
    alts
    -0.07
    æľīæŶåĢĻ
    -0.07
     Hayward
    -0.07
    è¿Ľè¡Įåħ¨éĿ¢
    -0.07
    POSITIVE LOGITS
    约èĢĮåIJĮ
    0.15
     alike
    0.12
    ä¸Ģèĩ´
    0.12
    åIJĦèĩªçļĦ
    0.11
    ä¸įåIJĮç¨ĭ度çļĦ
    0.11
    åIJĦèĩª
    0.10
    大åIJĮ
    0.10
    ä¸Ģèĩ´çļĦ
    0.10
    åIJĦæľī
    0.10
     nhau
    0.10
    Activations Density 0.227%

    No Known Activations