© 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. 28309
    Prev
    Next
    INDEX
    Explanations

    community development livelihood healthradiobuildingloan participatory

    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
    éģ¨æ¸¸
    -0.07
    åIJĦ大
    -0.07
    ä¸įèĭŁ
    -0.07
    åŁİå¸Ĥ群
    -0.06
    åŁİå¸Ĥ轨éģĵ交éĢļ
    -0.06
    è¡Įä¸ļåıijå±ķ
    -0.06
    çķħ
    -0.06
    åħ¨åĽ½äººæ°ij
    -0.06
    大æ´ĭ
    -0.06
    è¡°èĢģ
    -0.06
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.13
    åľ¨å½ĵåľ°
    0.13
    å½ĵåľ°
    0.13
    local
    0.11
     local
    0.11
    å½ĵåľ°äºº
    0.11
    ä¸İå½ĵåľ°
    0.11
    /local
    0.11
    æľ¬åľ°
    0.11
     grassroots
    0.11
    Activations Density 0.095%

    No Known Activations