© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    construction machinery loaders excavators forklifts

    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
     ticking
    -0.08
     Aerop
    -0.08
    åĻ¨ä»¶
    -0.08
    éķ¿è·ij
    -0.07
    çĭĻåĩ»
    -0.07
     swims
    -0.07
    åĪºå®¢
    -0.07
    æĸĩçIJĨ
    -0.07
    æĪĺæĸĹæľº
    -0.07
    å¯ĦçĶŁ
    -0.07
    POSITIVE LOGITS
    çļĦä½ľä¸ļ
    0.12
    æľºåĬ¨
    0.11
     hauling
    0.10
    ä½ľä¸ļ
    0.10
    åIJ¨
    0.10
     loaders
    0.10
    éĩįåŀĭ
    0.09
    æıIJé«ĺå·¥ä½ľæķĪçİĩ
    0.09
     maneuver
    0.09
    大åŀĭçļĦ
    0.09
    Activations Density 0.362%

    No Known Activations