© 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. 7888
    Prev
    Next
    INDEX
    Explanations

    k, -k, K

    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
    ungsver
    -0.08
    ONGL
    -0.08
    BILE
    -0.07
    èĢ¿èĢ¿
    -0.07
    æŃ¥æŃ¥é«ĺ
    -0.07
    欣èµıåĪ°
    -0.07
    çī©çļĦ
    -0.07
    ienz
    -0.07
    念念ä¸įå¿ĺ
    -0.07
    UFFIX
    -0.07
    POSITIVE LOGITS
    g
    0.08
    æ°ı
    0.07
    0.07
    大åݦ
    0.07
    åģ¿ä»ĺ
    0.07
    gai
    0.07
    soft
    0.07
    gam
    0.06
    æĺŃ
    0.06
     Knox
    0.06
    Activations Density 0.001%

    No Known Activations