© 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. 21340
    Prev
    Next
    INDEX
    Explanations

    numeric characters and punctuation

    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
     beyond
    -0.08
     Beyond
    -0.08
    Beyond
    -0.08
     (>
    -0.07
    elin
    -0.07
    è¶ħåĩºäºĨ
    -0.07
    Ke
    -0.07
     ~>
    -0.07
     ORM
    -0.07
    Tiny
    -0.07
    POSITIVE LOGITS
    代ä¹ĭ
    0.09
    è¾¾ä¸įåĪ°
    0.08
    .cast
    0.07
    ãĥ¼ãĥķ
    0.07
    è´¨çļĦ
    0.07
    casting
    0.07
    agged
    0.07
    å¹´åįĬ
    0.07
    ä¸Ń人
    0.07
    جات
    0.07
    Activations Density 0.097%

    No Known Activations