© 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. 24181
    Prev
    Next
    INDEX
    Explanations

    timeouts, sizes, scalings

    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
    avage
    -0.07
    ,arr
    -0.07
    asics
    -0.07
    mena
    -0.07
    oreach
    -0.07
    лежа
    -0.07
    (register
    -0.07
    ίκη
    -0.06
    imson
    -0.06
    ITAL
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    kins
    0.07
    ufact
    0.07
    紧贴
    0.07
    .Default
    0.07
    interv
    0.07
    æĬ±
    0.07
     interval
    0.06
    ạt
    0.06
     aggress
    0.06
    Activations Density 0.179%

    No Known Activations