© 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. 20573
    Prev
    Next
    INDEX
    Explanations

    Ferris, etone, Honeoye

    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
    åĽ½ä¹ĭ
    -0.07
    Ñģай
    -0.07
    è¦ĥ
    -0.07
    åĩºæ°´
    -0.07
    æĺ¯ä¸Ģ个éĿŀ常
    -0.06
    åĿĢ
    -0.06
    ä¼ļåIJĮ
    -0.06
    isex
    -0.06
    è®¤çľŁå®ĮæĪIJ
    -0.06
    åİŁåıijæĢ§
    -0.06
    POSITIVE LOGITS
    apura
    0.09
     Tavern
    0.08
    ÑijÑĢ
    0.08
    abol
    0.07
    ested
    0.07
    _malloc
    0.07
    ç´
    0.07
    کر
    0.07
    éĢī
    0.07
    ä¸Ģè¡Į
    0.07
    Activations Density 0.001%

    No Known Activations