© 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. 18868
    Prev
    Next
    INDEX
    Explanations

    nearby locations

    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
    è°Ľ
    -0.08
    ä¸İæĻ®éĢļ
    -0.07
    å±±æ´ŀ
    -0.06
    èĥ¡åIJĮ
    -0.06
     PIO
    -0.06
    æ¯ıç§į
    -0.06
    éĽªä¸Ń
    -0.06
    rero
    -0.06
    éķ¿ç¯ĩ
    -0.06
     Lantern
    -0.06
    POSITIVE LOGITS
     nearby
    0.11
    è¿ijåľ¨
    0.09
    Evt
    0.09
    ool
    0.08
     Nearby
    0.08
    hun
    0.08
    æ¶Īè´¹å¸Ĥåľº
    0.08
    åĴ«å°º
    0.08
     nearest
    0.07
    èijĹåIJįçļĦ
    0.07
    Activations Density 0.569%

    No Known Activations