© 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. 33557
    Prev
    Next
    INDEX
    Explanations

    sequential steps

    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
    ajer
    -0.07
     Zuk
    -0.07
    åľ¨æī§è¡Į
    -0.07
    æĪIJä½Ľ
    -0.07
    å¼±
    -0.07
    æľªæĿ¥
    -0.07
    ä»»ä½ķæŶåĢĻ
    -0.06
    yson
    -0.06
    tiques
    -0.06
     Mov
    -0.06
    POSITIVE LOGITS
    çĽ¸çŁ¥
    0.08
     ÑģобÑģÑĤвенно
    0.07
    éħĿ
    0.07
    ä¸Ģç³»åĪĹçļĦ
    0.07
    ISCO
    0.07
    orong
    0.07
    emain
    0.06
    λÏİ
    0.06
     ensuite
    0.06
    æĪijçŁ¥éģĵäºĨ
    0.06
    Activations Density 0.238%

    No Known Activations