© 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. 29153
    Prev
    Next
    INDEX
    Explanations

    set membership and subset notation

    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
    ä¹ĭæĦı
    -0.06
    æĤ²
    -0.06
    æĦı
    -0.06
    anges
    -0.06
    åIJ¦
    -0.06
    ä¹ĭæīĢ
    -0.06
    ullet
    -0.05
    éĿ©åij½çļĦ
    -0.05
    å¾Ĺåħ¶
    -0.05
    åı«äºº
    -0.05
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.09
    -register
    0.08
    Spo
    0.08
    esus
    0.08
    aspers
    0.07
    åĴĮåįķä½į
    0.07
    ofile
    0.07
    ffel
    0.07
    à¹Ģà¸Ļà¸Ńรà¹Į
    0.07
     Ñģпи
    0.07
    Activations Density 0.010%

    No Known Activations