© 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. 27965
    Prev
    Next
    INDEX
    Explanations

    scientific and socio-economic data

    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
    Spo
    -0.08
    inaldo
    -0.08
    кла
    -0.08
    -marker
    -0.08
    æĥ³å¾ĹåĪ°
    -0.08
    setStatus
    -0.07
    voirs
    -0.07
    æľīæīĢæĢĿ
    -0.07
    setId
    -0.07
    फà¥Ģ
    -0.07
    POSITIVE LOGITS
     scientific
    0.08
    èĩªçĦ¶çķĮ
    0.08
    akis
    0.07
    ç§ijåѦ
    0.06
    Science
    0.06
    çī©çIJĨ
    0.06
     sci
    0.06
     technical
    0.06
     physical
    0.06
    ÑģÑĥ
    0.06
    Activations Density 1.556%

    No Known Activations