© 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. 17428
    Prev
    Next
    INDEX
    Explanations

    brain areas and cortex

    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
     Klub
    -0.08
     homemade
    -0.07
    ä¸įåı¯æĬĹåĬĽ
    -0.07
    æŃ¥æŃ¥
    -0.07
    éĺ´éĺ³
    -0.07
    udu
    -0.07
    使çĶ¨æĸ¹ä¾¿
    -0.07
    åĹĵ
    -0.07
    èį¯çļĦ
    -0.07
    æ²īéĩįçļĦ
    -0.06
    POSITIVE LOGITS
     areas
    0.10
     cortex
    0.10
     regions
    0.09
    åĬŁèĥ½åĮº
    0.09
    大èĦij
    0.09
     area
    0.08
     receptive
    0.08
     devoted
    0.08
     dedicated
    0.08
     dedicate
    0.08
    Activations Density 0.118%

    No Known Activations