© 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. 17329
    Prev
    Next
    INDEX
    Explanations

    rotating, embellish, resolved, uniform

    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
    ä»ģæħĪ
    -0.07
    æ½
    -0.06
    纹路
    -0.06
    лÑĩа
    -0.06
    æĪĺèĥľ
    -0.06
     undefeated
    -0.06
    æľīåģ¿
    -0.06
     kaas
    -0.06
    etas
    -0.06
    ugas
    -0.06
    POSITIVE LOGITS
    _HOOK
    0.07
    ä¸Ģçķª
    0.07
    æ¡ĥæĿİ
    0.07
    orma
    0.07
    è°Ń
    0.07
    æĪĸå¤ļ个
    0.07
    äºĨä¸Ģçķª
    0.06
    _likelihood
    0.06
    éĢļè¿ĩè¿ĻäºĽ
    0.06
    OrCreate
    0.06
    Activations Density 0.488%

    No Known Activations