© 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. 41202
    Prev
    Next
    INDEX
    Explanations

    two, 2, dual

    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¸ī个æĸ¹éĿ¢
    -0.08
    ãĤį
    -0.07
    ä¹Łæĺ¯æĪij
    -0.07
    avera
    -0.07
    lian
    -0.07
     поÑģÑĥ
    -0.07
    ä¸įèµ°
    -0.07
    gai
    -0.07
    ä¸ī个éĺ¶æ®µ
    -0.07
    ä¸īèĢħ
    -0.07
    POSITIVE LOGITS
    è¿Ļ两个
    0.09
     duo
    0.09
    çļĦ两个
    0.08
    ä¸Ģ对
    0.08
    pair
    0.08
    æĺ¯ä¸Ģ对
    0.08
     pair
    0.08
    éĢĻåħ©åĢĭ
    0.08
    è¿Ļ两ç§į
    0.08
     Duo
    0.07
    Activations Density 0.084%

    No Known Activations