© 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. 27466
    Prev
    Next
    INDEX
    Explanations

    length, mass, density, group

    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
     Viale
    -0.07
    anders
    -0.07
    å·¥ç§į
    -0.07
     devid
    -0.07
    _IMPLEMENT
    -0.06
    erta
    -0.06
    ä¸ĸ
    -0.06
    ptica
    -0.06
    ä¹Łæĺ¯åįģåĪĨ
    -0.06
    indi
    -0.06
    POSITIVE LOGITS
    å¯ŀ
    0.07
    ä¸ŀ
    0.07
    orch
    0.07
    åѦåı²
    0.07
    çĿĢå°ı
    0.06
    ãģ¾ãģ¤
    0.06
    irst
    0.06
    çŁ¢
    0.06
    ç£ĭ
    0.06
     ÑģпÑĸв
    0.06
    Activations Density 0.011%

    No Known Activations