© 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. 18833
    Prev
    Next
    INDEX
    Explanations

    Mojibake or special characters

    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
    ç»Ħç»Ħéķ¿
    -0.07
    çĦ¶åIJİæĺ¯
    -0.07
    æĭ¿åĩºæĿ¥
    -0.07
    çļĦæĺ¯ä»Ģä¹Ī
    -0.07
    åħ¬å¢ĵ
    -0.07
    æĨ¬
    -0.07
    onsor
    -0.07
     distrib
    -0.07
    èĴIJ
    -0.07
    <![
    -0.07
    POSITIVE LOGITS
    æķħéĢī
    0.08
    amet
    0.07
    åľ¨åį³
    0.07
    æķħ
    0.07
    ä¹Łå°±
    0.07
    以ä¸Ĭ
    0.07
     váºŃy
    0.06
    æľ¬é¢ĺçŃĶæ¡Ī
    0.06
    缮
    0.06
    çļĨ
    0.06
    Activations Density 0.002%

    No Known Activations