© 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. 7734
    Prev
    Next
    INDEX
    Explanations

    all or any

    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
    vez
    -0.08
    ition
    -0.07
    hia
    -0.07
    ảo
    -0.07
    æĿĢ伤
    -0.07
    lama
    -0.07
    dak
    -0.07
    åŃ
    -0.07
     disso
    -0.06
    AINS
    -0.06
    POSITIVE LOGITS
     imaginable
    0.08
    elter
    0.07
    /all
    0.07
    éļ¾åº¦çļĦ
    0.07
    antu
    0.07
     conceivable
    0.07
    æĥħåĨµæĿ¥çľĭ
    0.07
     تÙĤرÙĬب
    0.07
    год
    0.06
    é¡¿äºĨ
    0.06
    Activations Density 0.059%

    No Known Activations