© 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. 9274
    Prev
    Next
    INDEX
    Explanations

    consulting and outsourcing services

    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
    åŃ¦ä»¥èĩ´
    -0.07
    åĽŀçļĦ
    -0.06
    åŁºäºİ
    -0.06
     occ
    -0.06
    ä¸Ģ空
    -0.06
    -directed
    -0.06
    对ä¸įåIJĮ
    -0.05
    .VERSION
    -0.05
    ×¨×Ľ×ª
    -0.05
    ä¸Ģå¥Ĺ
    -0.05
    POSITIVE LOGITS
    çķĮçļĦ
    0.10
    çķĮ
    0.09
    zul
    0.09
     world
    0.08
    etton
    0.08
     mainstream
    0.08
    åįĥåįĥä¸ĩ
    0.08
    eros
    0.08
    è¡Įä¸ļ
    0.08
    æŀĹçĭ¬
    0.08
    Activations Density 0.613%

    No Known Activations