© 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. 21141
    Prev
    Next
    INDEX
    Explanations

    search of, aggregate ., culture ., action on, sale at, development

    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
    клÑİÑĩа
    -0.09
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    åħ¶ä¸º
    -0.08
    nicz
    -0.08
    alysis
    -0.08
     "[%
    -0.07
     BinaryTree
    -0.07
     też
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    iesel
    -0.07
    POSITIVE LOGITS
    /on
    0.09
    Ùį
    0.08
    /by
    0.08
    /at
    0.07
    گاÙĩ
    0.07
    æĪĸåľ¨
    0.07
    edly
    0.07
    çĺ¢
    0.07
    /off
    0.07
    /out
    0.07
    Activations Density 0.655%

    No Known Activations