© 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. 47164
    Prev
    Next
    INDEX
    Explanations

    fat, single, characters, number, HDF, server, stressful, delivery

    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
    edan
    -0.08
    ilig
    -0.08
    ³
    -0.08
    æ²½
    -0.07
    oline
    -0.07
    å·¡
    -0.07
    ụng
    -0.07
    ãģĽãĤĵ
    -0.07
    åł¡
    -0.07
    æ¯Ķæĸ¹
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.11
    èĢĮè¿ĻäºĽ
    0.09
    èĢĮä¸Ķæĺ¯
    0.09
    ä¸Ķåħ·æľī
    0.09
    ãģĹãģĭãĤĤ
    0.08
    èĢĮä¸Ķ
    0.08
    èĢĮè¿Ļ个
    0.07
    åIJ«
    0.07
    —with
    0.07
    ä¸ŃåIJ«æľī
    0.07
    Activations Density 0.255%

    No Known Activations