© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47893
    Prev
    Next
    INDEX
    Explanations

    variable assignments or method calls

    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
    áĭ«
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    èĢĮçŁ¥
    -0.07
    建åįİ
    -0.07
    è¿ľè¿ij
    -0.07
    azzi
    -0.07
    èĢĮæĪIJ
    -0.07
    DELAY
    -0.07
    æĬĺä¸į
    -0.07
    strup
    -0.07
    POSITIVE LOGITS
    åıĺ为
    0.08
    Ùģر
    0.08
     lúc
    0.07
    ä»ħæѤ
    0.07
     becomes
    0.07
    æĶ¹ä¸º
    0.07
    è¿Ļæīį
    0.07
    ä¸įèĩªè§ī
    0.07
    pread
    0.07
    èĩªçŁ¥
    0.07
    Activations Density 0.002%

    No Known Activations