© 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. 39037
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    asm
    -0.08
    abs
    -0.07
    çŃīéĩįè¦ģ
    -0.07
    央
    -0.07
    åīĤçŃī
    -0.07
    æ²¾
    -0.07
    avan
    -0.07
    ades
    -0.07
    rico
    -0.07
    ndata
    -0.07
    POSITIVE LOGITS
    ä¸Ĭä¸ĢæĿ¡
    0.08
    åīįè¿°
    0.07
    éĢĤåIJĪäºİ
    0.07
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    çŁ¥éģĵä½ł
    0.07
    åħ¶çī¹å¾ģåľ¨äºİ
    0.07
    æīĢè¿°çļĦ
    0.07
    çļĦä¸Ģé¢Ĺ
    0.07
    ä¸Ĭè¿°
    0.07
    |min
    0.07
    Activations Density 0.179%

    No Known Activations