© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    locations like gym, work, and prisons

    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
    åľ¨éĩĮéĿ¢
    -0.10
    åľ¨å·¥ä½ľä¸Ĭ
    -0.10
    åľ¨åŃ¦ä¹łä¸Ĭ
    -0.09
    à¹ĥà¸Ļรà¹Īาà¸ĩà¸ģาย
    -0.08
    åľ¨è®¾è®¡
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    åľ¨ä¸ĬéĿ¢
    -0.08
    åľ¨è¯¥
    -0.08
    åľ¨è¿ĻåĦ¿
    -0.08
    åħĪçĶŁåľ¨
    -0.08
    POSITIVE LOGITS
    æĪĸåľ¨
    0.10
     nanti
    0.10
     angekommen
    0.09
    表çݰ为
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.09
    åĴĮåľ¨
    0.08
    主è¦ģ表çݰ为
    0.08
     ÙĪÙģÙĬ
    0.08
     ×ķ×ij
    0.08
    ghan
    0.07
    Activations Density 1.178%

    No Known Activations