© 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. 32957
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and Latin phrases

    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
    好似
    -0.08
    ossi
    -0.07
    为ä¸Ģ
    -0.06
    oyo
    -0.06
    å°ıå°ı
    -0.06
    jär
    -0.06
    å°±ä»İ
    -0.06
    anus
    -0.06
    yd
    -0.06
    j
    -0.06
    POSITIVE LOGITS
     zufolge
    0.11
    artige
    0.10
     ÑħваÑĤ
    0.10
    λάÏĩιÏĥ
    0.09
     ÑħваÑĤи
    0.08
    ä¸įå®Įåħ¨ç»Łè®¡
    0.08
     ÑħваÑĤаеÑĤ
    0.08
    wegen
    0.08
    å¾·åįİ
    0.08
    *))
    0.08
    Activations Density 0.038%

    No Known Activations