© 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. 30186
    Prev
    Next
    INDEX
    Explanations

    Lang names

    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¸Ńæľī
    -0.07
    AAAAAAAA
    -0.07
    olvers
    -0.06
    ä¸įåıĬ
    -0.06
    è¸
    -0.06
    ãģ£ãģ¨
    -0.06
    (+
    -0.06
    Õ®
    -0.06
    .ones
    -0.06
    anky
    -0.06
    POSITIVE LOGITS
    ä¹ĭåīij
    0.07
    andi
    0.07
     **âĸł
    0.07
    åĺĮ
    0.07
    å·¥ç¨ĭéĻ¢
    0.07
    çļĦ女åĦ¿
    0.07
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    0.07
    ļľ
    0.07
    pret
    0.07
    apis
    0.07
    Activations Density 0.333%

    No Known Activations