© 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. 32107
    Prev
    Next
    INDEX
    Explanations

    punctuation and closing delimiters

    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
    azine
    -0.08
    éĬĺ
    -0.07
    楽
    -0.07
    zinho
    -0.07
    éĺ¿å¸ĥ
    -0.07
     sbar
    -0.07
    ationally
    -0.06
    翼翼
    -0.06
    ERING
    -0.06
    entifier
    -0.06
    POSITIVE LOGITS
    oby
    0.07
    æµ·
    0.07
    tek
    0.07
    ä¸ĭåIJĮ
    0.07
    çļĦä¸ĢéĿ¢
    0.06
    ave
    0.06
     lay
    0.06
    èĩ¼
    0.06
    taj
    0.06
    çļĦä¸Ģ侧
    0.06
    Activations Density 0.107%

    No Known Activations