© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26801
    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
    ÄĻb
    -0.08
    ÑĤеÑĢе
    -0.07
    /of
    -0.07
    嫦
    -0.07
    arkan
    -0.07
    pector
    -0.07
    kasten
    -0.07
     fermo
    -0.07
    è¿ĶåĽŀåĪĹ表
    -0.06
    abh
    -0.06
    POSITIVE LOGITS
    /how
    0.11
    ç±»åŀĭçļĦ
    0.10
     именно
    0.10
     tepatnya
    0.09
     kinds
    0.09
     Ñģаме
    0.09
     else
    0.09
    æł·çļĦ
    0.09
     exactly
    0.08
     kind
    0.08
    Activations Density 0.212%

    No Known Activations