© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    BIND
    -0.08
    -Sah
    -0.08
    åĵī
    -0.07
    otá
    -0.07
    ipp
    -0.07
    áŀ·
    -0.07
    åľ¨ç¬¬
    -0.07
    ä½łè¿ĺåľ¨
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    ä¹İåħ¶
    -0.07
    POSITIVE LOGITS
    çľĭå¾Ĺ
    0.06
     ru
    0.06
    ago
    0.06
    emberg
    0.06
     prest
    0.06
    åĪĺæĸĩ
    0.06
    夫
    0.06
     followed
    0.06
    æµ®
    0.05
    ẻ
    0.05
    Activations Density 0.003%

    No Known Activations