© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    skeletal muscle, div, Desktop

    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
    anter
    -0.08
    åIJĦç»Ħ
    -0.07
    berge
    -0.07
    aw
    -0.07
    awal
    -0.07
    av
    -0.06
    æľīåı¯èĥ½ä¼ļ
    -0.06
    ibu
    -0.06
    æĻļå®ī
    -0.06
    天亮
    -0.06
    POSITIVE LOGITS
    åħ·æľī以ä¸ĭ
    0.11
    以ä¸ĭåĩłçĤ¹
    0.10
    çļĦçī¹çĤ¹
    0.09
     Ãĸzell
    0.08
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.08
     {}:
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.08
    æľī以ä¸ĭ
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.08
    Activations Density 0.285%

    No Known Activations