© 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. 17000
    Prev
    Next
    INDEX
    Explanations

    names ending in -ley/-ey/-ia/-er

    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
    è¿ĩä¸įåİ»
    -0.07
    ï¸ı
    -0.07
    à¹Ģà¸Ķียว
    -0.06
    é³ŀ
    -0.06
     '&#
    -0.06
    à¸Ĺà¹Īาà¸Ļ
    -0.06
    å²ĽçļĦ
    -0.06
    èĥĢ
    -0.06
    /dd
    -0.06
     à¸Ĺà¹Īาà¸Ļ
    -0.06
    POSITIVE LOGITS
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.08
    shaw
    0.08
    ä½ľåĪĻ
    0.07
    å®īæģ¯
    0.07
    åı¯æ¢¦
    0.07
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.07
     aka
    0.07
    æĸ¯å·´
    0.07
    atico
    0.07
    æĽ¾èİ·
    0.07
    Activations Density 0.190%

    No Known Activations