© 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. 60153
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

    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¿Ļæĺ¯æĪij们
    -0.08
    ³
    -0.07
    parte
    -0.07
    è¿Ļæĺ¯ä»ĸ
    -0.07
    æIJª
    -0.06
    cury
    -0.06
    ajian
    -0.06
    cgi
    -0.06
    è¦ģ注æĦı
    -0.06
    acct
    -0.06
    POSITIVE LOGITS
    xis
    0.07
    æľĢæľīæķĪçļĦ
    0.07
    enschaft
    0.07
    人说
    0.07
    elia
    0.07
    èİ·èµŀ
    0.07
    fax
    0.07
    æľĢæ·±çļĦ
    0.07
    æĪij认为
    0.07
    erring
    0.07
    Activations Density 0.004%

    No Known Activations