© 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. 16573
    Prev
    Next
    INDEX
    Explanations

    expected value or benchmark

    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
    åĭĩèĢħ
    -0.08
    èĤĩ
    -0.06
    igans
    -0.06
    steller
    -0.06
    _tex
    -0.06
    кÑĤо
    -0.06
    cede
    -0.06
    åĬłç´¢
    -0.06
    ä½łèº«è¾¹
    -0.06
    glieder
    -0.06
    POSITIVE LOGITS
    æłĩåĩĨè¦ģæ±Ĥ
    0.14
    .expected
    0.13
    é¢ĦæľŁ
    0.13
     expectations
    0.12
     expected
    0.12
    çļĦé¢ĦæľŁ
    0.12
     Expected
    0.12
     expectation
    0.12
    expected
    0.11
     benchmark
    0.11
    Activations Density 0.147%

    No Known Activations