© 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. 19398
    Prev
    Next
    INDEX
    Explanations

    parentheses 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
    ikh
    -0.07
    çī§ç¾Ĭ
    -0.07
    iras
    -0.07
    åĮĸ管çIJĨ
    -0.07
    azi
    -0.07
    ikle
    -0.07
    缴æİ¥æĬĬ
    -0.07
     hence
    -0.07
    wyn
    -0.07
    åĬłæĸ¯
    -0.06
    POSITIVE LOGITS
    è¿Ļä¸ĢæŃ¥
    0.09
    å¤ĩçĶ¨
    0.07
    ť
    0.07
    roku
    0.06
    omit
    0.06
    å¤ĩ注
    0.06
    åı¯ä»¥éĩĩçĶ¨
    0.06
     dó
    0.06
    await
    0.06
    osz
    0.06
    Activations Density 0.036%

    No Known Activations