© 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. 60163
    Prev
    Next
    INDEX
    Explanations

    punctuation and code separators

    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
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.08
    ede
    -0.07
     firstly
    -0.07
    edin
    -0.07
    æĸ°éĹ»å®¢æĪ·ç«¯
    -0.07
    CLUDING
    -0.07
    apers
    -0.07
    è¿ĩå¹´çļĦ
    -0.07
    és
    -0.06
    uner
    -0.06
    POSITIVE LOGITS
    æīĢ以说
    0.09
    æīĢ以对
    0.08
    ä»İèĢĮ
    0.08
     Therefore
    0.08
    è¿Ļä¹Ł
    0.08
    åĽłæѤ
    0.08
     Thus
    0.08
    æīĢ以çİ°åľ¨
    0.08
     similarly
    0.08
    è¿Ļæĺ¯å¯¹
    0.08
    Activations Density 0.002%

    No Known Activations