© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42587
    Prev
    Next
    INDEX
    Explanations

    positional directions

    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
    ammers
    -0.08
    åĬ³ç´¯
    -0.08
     Zwe
    -0.07
    è¾Ł
    -0.07
    itle
    -0.07
    å¿ĥæĤ¦
    -0.07
    æł¼
    -0.06
     ailleurs
    -0.06
     اÙĦÙĦا
    -0.06
    ===============
    -0.06
    POSITIVE LOGITS
     쪽
    0.11
     ÑģÑĤоÑĢонÑĥ
    0.11
    æĸ¹åIJij
    0.10
    è¶ĬæĿ¥è¶Ĭè¿ij
    0.09
    æĸ¹åIJijçļĦ
    0.09
     direction
    0.08
    çļĦæĸ¹åIJij
    0.08
     stronÄĻ
    0.08
    åģ´ãģ«
    0.08
     toward
    0.08
    Activations Density 0.081%

    No Known Activations