© 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. 64925
    Prev
    Next
    INDEX
    Explanations

    package ch.ethz.ssh2.packets

    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
    óng
    -0.07
    odr
    -0.07
    è®©æĽ´å¤ļ人
    -0.07
     Sá
    -0.07
    odka
    -0.07
    ä¸įä½ıäºĨ
    -0.07
    à¸ĸ
    -0.06
    æ·¡
    -0.06
    opping
    -0.06
    涵
    -0.06
    POSITIVE LOGITS
    pretty
    0.06
    ieri
    0.06
    å¬Į
    0.06
    è°Ĵ
    0.06
    ä¿Ĺ
    0.06
     pret
    0.06
    âĶģ
    0.06
    ayanan
    0.06
    åį
    0.06
    ecchio
    0.06
    Activations Density 0.391%

    No Known Activations