© 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. 50786
    Prev
    Next
    INDEX
    Explanations

    a recognized commentator

    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
    uku
    -0.07
    强身
    -0.07
    orro
    -0.07
    emun
    -0.07
    orget
    -0.07
    мигÑĢа
    -0.07
     mutu
    -0.07
     svil
    -0.07
     ελλην
    -0.07
    女æĢ§ãģĮ
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģåijĺ
    0.12
    åIJįåī¯åħ¶å®ŀçļĦ
    0.10
    主è¦ģçļĦ
    0.08
    æ½ľåľ¨çļĦ
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
     pelaksana
    0.08
    çļĦä¸ĢåIJį
    0.07
    è¿Ļ个è§Ĵèī²
    0.07
    座ä¸Ĭ
    0.07
    ä¸įæĬĺä¸įæī£
    0.07
    Activations Density 1.157%

    No Known Activations