© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    markdown links with http

    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
    éĿ³
    -0.07
    /
    -0.06
    éļ
    -0.06
    as
    -0.06
    era
    -0.06
    ed
    -0.06
    ↵                ↵
    -0.06
    æĨ¾
    -0.06
    -0.06
    os
    -0.06
    POSITIVE LOGITS
    олÑĮ
    0.10
    åIJĦç§įåIJĦæł·
    0.09
    åħ¨å¿ĥåħ¨æĦı
    0.08
    åħ·ä½ĵåĨħ容
    0.08
    éĺ¿æĭī伯
    0.08
    ICODE
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    åıĬ使çĶ¨
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    ATUS
    0.08
    Activations Density 0.085%

    No Known Activations