© 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. 41262
    Prev
    Next
    INDEX
    Explanations

    explaining or commentary

    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
    ennes
    -0.08
    说起æĿ¥
    -0.07
    iform
    -0.07
    emento
    -0.07
    periment
    -0.07
    å¾Ĺæīĭ
    -0.07
    æİĤ
    -0.07
     unprotected
    -0.07
    æīĢ欲è¨Ģ
    -0.07
    å®ŀéªĮä¸Ń
    -0.07
    POSITIVE LOGITS
     interpretations
    0.14
     interpretation
    0.13
     interpreting
    0.13
     interpret
    0.12
    interpret
    0.12
    解读
    0.12
     Interpret
    0.11
     interpre
    0.11
     commentary
    0.10
     interpretación
    0.10
    Activations Density 0.029%

    No Known Activations