© 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. 12570
    Prev
    Next
    INDEX
    Explanations

    .helpers

    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
    ÑĥÑĤа
    -0.07
    eton
    -0.07
    umb
    -0.06
    ä¼´
    -0.06
     pys
    -0.06
    vern
    -0.06
    renched
    -0.06
    æīĢæľīçļĦ
    -0.06
    æĹ¥çĶ¨åĵģ
    -0.06
    Ñģом
    -0.06
    POSITIVE LOGITS
    IBIL
    0.07
    /compiler
    0.07
    ØŃاب
    0.07
    lots
    0.07
    íĥĿ
    0.07
    ãģ«ãģĭãģı
    0.07
    parseFloat
    0.07
    -browser
    0.07
    memcmp
    0.07
    ä¸įæĦģ
    0.07
    Activations Density 0.048%

    No Known Activations