© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    plane or line

    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
    æŃ¥å±¥
    -0.07
    饱满
    -0.07
    SizeMode
    -0.07
     complete
    -0.07
    æ´ŀ天
    -0.07
    ARGS
    -0.06
    sworth
    -0.06
    agy
    -0.06
    è½¬çŁ©
    -0.06
     Garan
    -0.06
    POSITIVE LOGITS
     plane
    0.09
    Plane
    0.09
     Plane
    0.08
    plane
    0.08
    _plane
    0.08
    å¹³éĿ¢
    0.08
    -plane
    0.08
     planes
    0.08
    è¾¹çļĦ
    0.08
    opin
    0.08
    Activations Density 0.009%

    No Known Activations