© 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. 29413
    Prev
    Next
    INDEX
    Explanations

    download or read file

    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
    æ³ī
    -0.08
    ynd
    -0.07
    ä¸įèĤ¯
    -0.07
    accio
    -0.07
    ÑĤеÑĢа
    -0.07
    çĽ
    -0.06
    almaz
    -0.06
    ocking
    -0.06
    วา
    -0.06
    éĻĨ
    -0.06
    POSITIVE LOGITS
    iano
    0.08
    etton
    0.08
    æ´Ľæĸ¯
    0.07
    åIJijæĹ¥
    0.07
    icture
    0.07
    çĸijéļ¾
    0.07
    çłĶ究ä¼ļ
    0.07
    _ls
    0.07
    çĶŁæ´»ä¼ļ
    0.07
    åIJĦç§įåIJĦæł·çļĦ
    0.07
    Activations Density 0.001%

    No Known Activations