© 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. 2694
    Prev
    Next
    INDEX
    Explanations

    diameter metric

    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
    è¿ľ
    -0.07
    åĢįæķ°
    -0.07
    åĢį
    -0.07
    åįģåĢį
    -0.06
    ç´¯
    -0.06
     Abr
    -0.06
    è¿ľä½İäºİ
    -0.06
    ä¹Ŀå¹´
    -0.06
     fór
    -0.06
    åıª
    -0.06
    POSITIVE LOGITS
     slightly
    0.20
    çķ¥
    0.17
    çķ¥å¾®
    0.17
    çķ¥æľī
    0.16
     légèrement
    0.16
     slight
    0.15
     leggermente
    0.15
    ç¨į
    0.14
    ç¨įæľī
    0.14
    ç¨įå¾®
    0.14
    Activations Density 0.042%

    No Known Activations