© 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. 15250
    Prev
    Next
    INDEX
    Explanations

    convex shapes and mathematics

    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
    æĬ½
    -0.08
     اÙĦباÙĦ
    -0.07
    èĴ
    -0.06
    æįī
    -0.06
     bout
    -0.06
    ighb
    -0.06
     оÑĤÑĤе
    -0.06
    æ½®æ±IJ
    -0.06
    annel
    -0.06
    æĮ½
    -0.06
    POSITIVE LOGITS
     convex
    0.10
    å½¢çĬ¶çļĦ
    0.09
    Coder
    0.08
    plex
    0.08
    çķĮå®ļ
    0.08
    åĩ¸
    0.08
    intersection
    0.08
    Membership
    0.07
    éĻIJåĪ¶
    0.07
     intersection
    0.07
    Activations Density 0.012%

    No Known Activations