© 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. 17373
    Prev
    Next
    INDEX
    Explanations

    piece of, set of, group of

    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
    ijų
    -0.07
    è¿Ļä¸ªä¸ľè¥¿
    -0.07
    tools
    -0.07
    ovit
    -0.07
    æīĢ欲
    -0.07
    اÙģÙĬ
    -0.07
    egel
    -0.07
    fiz
    -0.07
    è¿Ļ个çĶ·äºº
    -0.07
    fmt
    -0.07
    POSITIVE LOGITS
    -of
    0.08
    å¦į
    0.07
    ä¸Ĭ人
    0.07
    å·¥ä½ľåĪ¶
    0.07
     of
    0.07
     Fucking
    0.06
    à¸ĩาà¸Ļ
    0.06
    åIJĪåIJĮæŶ
    0.06
    _of
    0.06
    é£Łäºĭ
    0.06
    Activations Density 0.615%

    No Known Activations