© 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. 62421
    Prev
    Next
    INDEX
    Explanations

    Tenth Circuit

    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
    àªļ
    -0.07
    iola
    -0.07
    osition
    -0.07
    angg
    -0.07
    ÑĨина
    -0.07
    å°ıåѦè¯Ńæĸĩ
    -0.07
    ä¸Ģç»ıåıijçİ°
    -0.07
    obet
    -0.07
    æ¯ıå¹³æĸ¹ç±³
    -0.06
    å¿ħé¡»çĶ±
    -0.06
    POSITIVE LOGITS
    URLConnection
    0.08
    天山
    0.07
    .Companion
    0.07
     numeros
    0.07
    åľ°éģĵ
    0.07
    arga
    0.07
    .plist
    0.07
    olik
    0.07
     اÙĦÙĦÙİÙijÙĩ
    0.07
    usia
    0.07
    Activations Density 0.002%

    No Known Activations