© 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. 18489
    Prev
    Next
    INDEX
    Explanations

    save time and money

    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
    มูล
    -0.08
    iesto
    -0.07
    åѦæĬ¥
    -0.07
    ewan
    -0.07
    çļĦèī¯å¥½
    -0.07
    jana
    -0.07
    IRD
    -0.07
    åľ°äºļ
    -0.07
    念
    -0.07
    zl
    -0.07
    POSITIVE LOGITS
    çľģåĬĽ
    0.12
    çľģäºĭ
    0.10
    çľģæŶ
    0.10
    èĬĤçľģ
    0.10
    ç®ĢåĮĸ
    0.10
    ç¹ģ
    0.10
    æĩĴ人
    0.09
    èĬĤçľģäºĨ
    0.09
    çľģåİ»
    0.09
    ä¸įçĶ¨åĨį
    0.09
    Activations Density 0.223%

    No Known Activations