© 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. 12347
    Prev
    Next
    INDEX
    Explanations

    years, hours, weeks

    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
    éģ¥éģ¥
    -0.08
    į
    -0.07
    åįĬ个
    -0.07
    .Dispatch
    -0.07
     μÏĢ
    -0.07
    .nodeType
    -0.07
    tering
    -0.07
    rech
    -0.07
    å¤ļå¤ļ
    -0.07
     agu
    -0.07
    POSITIVE LOGITS
     namely
    0.11
    åĪĨåĪ«æĺ¯
    0.09
     à¹Ħà¸Ķà¹īà¹ģà¸ģà¹Ī
    0.09
    nam
    0.08
    诸å¦Ĥ
    0.08
     nämlich
    0.08
    åIJįåŃĹåı«
    0.08
    åĪĨåĪ¥æĺ¯
    0.08
     viz
    0.08
    主è¦ģéĽĨä¸Ńåľ¨
    0.07
    Activations Density 0.125%

    No Known Activations