© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    mathematical and unit quantities

    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
    åįĬæŃ¥
    -0.09
     Aper
    -0.08
    velt
    -0.08
    è·¯éĢı
    -0.08
    -vars
    -0.08
    ç¾İå¾Ĺ
    -0.08
    ťa
    -0.08
    ->__
    -0.08
     ÐŁÐ¾ÑģÑĤан
    -0.08
    åIJİèĢħ
    -0.08
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.07
    ç¥Ģ
    0.06
    nar
    0.06
    è¢ħ
    0.06
    (s
    0.06
     z
    0.06
    ãģ¡
    0.06
    æĮĩçļĦ
    0.05
    ZO
    0.05
     vs
    0.05
    Activations Density 0.382%

    No Known Activations