© 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. 63106
    Prev
    Next
    INDEX
    Explanations

    freezing temperatures and conditions

    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
    åĵī
    -0.10
    jenigen
    -0.09
    clearfix
    -0.08
    à¸Ħวัà¸Ļ
    -0.08
    äºijéĽĨ
    -0.08
    pter
    -0.08
    ثة
    -0.08
    antum
    -0.07
    yac
    -0.07
     mẽ
    -0.07
    POSITIVE LOGITS
    /de
    0.08
    udem
    0.08
     напÑĢ
    0.07
     ìĸ¼
    0.07
    æĪIJå½¢
    0.07
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.07
    åĸī
    0.07
    æľŁ
    0.07
    åĨ»
    0.07
    åĩĿåĽº
    0.07
    Activations Density 0.017%

    No Known Activations