© 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. 29753
    Prev
    Next
    INDEX
    Explanations

    subtropical, Buddhism, bathtub, temperate, typographical, derivative

    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
    ä¸Ģç«Ļ
    -0.09
    æīĢåIJij
    -0.08
    èŁĢ
    -0.07
    ç«ĻåĪ°
    -0.07
    ÚĺÙĩ
    -0.07
    ä¸Ńå¤ĸ
    -0.07
    çļĦæ°ijæĹı
    -0.07
    æĺ¨å¤©çļĦ
    -0.07
    isel
    -0.06
    å¤ĸ滩
    -0.06
    POSITIVE LOGITS
    ¾
    0.08
    mgr
    0.07
    ä»ħä¾ĽåıĤèĢĥ
    0.07
    纪å½ķ
    0.07
    纾
    0.06
    Inactive
    0.06
    æĺ¯è¯¥
    0.06
    寧
    0.06
    æĨ¬
    0.06
    -sama
    0.06
    Activations Density 0.025%

    No Known Activations