© 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. 43682
    Prev
    Next
    INDEX
    Explanations

    a sequence contains

    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
    åĬ¨è¾Ħ
    -0.09
    ãĤ¤ãĥĦ
    -0.08
    è¦ģç»ĵåIJĪ
    -0.08
    _VIRTUAL
    -0.08
    fea
    -0.08
     Westbrook
    -0.08
     dụ
    -0.08
     obej
    -0.08
    locales
    -0.08
    nable
    -0.08
    POSITIVE LOGITS
    èĩ³å°ij
    0.07
    bai
    0.07
    ↵
    0.07
    æģ°å¥½
    0.07
     (
    0.07
     either
    0.06
    ä¸įå°ijäºİ
    0.06
    Âł
    0.06
     XOR
    0.06
    åı¸
    0.06
    Activations Density 0.134%

    No Known Activations