© 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. 15615
    Prev
    Next
    INDEX
    Explanations

    questions starting with what

    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
    صرة
    -0.09
    yor
    -0.08
    obl
    -0.08
    微信æī«ä¸Ģæī«
    -0.08
    rire
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.08
    æĴij
    -0.07
    íħ
    -0.07
    å¿ĥäºĨ
    -0.07
    åľŁå»º
    -0.07
    POSITIVE LOGITS
    serter
    0.07
    bj
    0.06
    X
    0.06
    bard
    0.06
     Desta
    0.06
    inkin
    0.06
    è¨
    0.06
    ÑĢо
    0.06
    ãģĽ
    0.06
    ZZ
    0.06
    Activations Density 0.001%

    No Known Activations