© 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. 63398
    Prev
    Next
    INDEX
    Explanations

    leetcode.com, Google, Euler, CodeWars

    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
    /vnd
    -0.07
    /documents
    -0.07
    addTo
    -0.06
    åĬ©
    -0.06
    si
    -0.06
    ä¸įåĩ¡
    -0.06
    èµĦéĩijçļĦ
    -0.06
    Foto
    -0.06
    ä¸İä¼Ĺä¸įåIJĮçļĦ
    -0.06
    åı¤çŃĿ
    -0.06
    POSITIVE LOGITS
    åĪ·é¢ĺ
    0.09
    åİŁé¢ĺ
    0.08
    æĮijæĪĺæĢ§
    0.08
    æĮijæĪ¦
    0.07
    æ¯ıæĹ¥ä¸Ģ
    0.07
    '](
    0.07
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    egin
    0.07
    åĩºä¸Ģéģĵ
    0.07
    精讲
    0.07
    Activations Density 0.026%

    No Known Activations