© 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. 28158
    Prev
    Next
    INDEX
    Explanations

    warning signs, traffic signals, cameras, lights, fences

    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
    éĺģ楼
    -0.09
    ãĥĵãĥ«
    -0.07
     Threads
    -0.07
    éģ¨æ¸¸
    -0.07
     rist
    -0.07
     Embal
    -0.07
    室温
    -0.07
    éĴ»å¤´
    -0.06
    ä¸Ģæ»´
    -0.06
    ä¸įèĭŁ
    -0.06
    POSITIVE LOGITS
     vandal
    0.09
     erected
    0.09
     signage
    0.09
     ìĦ¤ì¹ĺ
    0.09
    å®īè£ħåľ¨
    0.09
     vandalism
    0.09
    ç»´æĬ¤
    0.09
    ãĤĴè¨Ńç½®
    0.09
    çŃī设æĸ½
    0.09
    设æĸ½
    0.08
    Activations Density 0.122%

    No Known Activations