© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39586
    Prev
    Next
    INDEX
    Explanations

    read messages or sequel was

    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
    º
    -0.08
     compañ
    -0.07
     thoa
    -0.07
    attes
    -0.07
    ä¸ŃæĭĽ
    -0.07
    (er
    -0.07
    ritz
    -0.07
    ä¸İåIJ¦
    -0.06
    ä¼ļé¦Ĩ
    -0.06
    xaa
    -0.06
    POSITIVE LOGITS
    lec
    0.08
    å²Ĺ
    0.07
    ÑĥÑĢ
    0.06
    å·§
    0.06
    ......
    0.06
    okol
    0.06
    osas
    0.06
    ấu
    0.06
    æĸ½æķĻ
    0.06
    éĢıæĺİçļĦ
    0.06
    Activations Density 0.037%

    No Known Activations