© 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. 28783
    Prev
    Next
    INDEX
    Explanations

    programming or structured text context

    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
    .template
    -0.07
    象
    -0.07
    宸
    -0.07
    注
    -0.06
    鼶åĶ®
    -0.06
    ottes
    -0.06
     Trin
    -0.06
    çļĦåİŁçIJĨ
    -0.06
    Че
    -0.06
    è¾°
    -0.06
    POSITIVE LOGITS
    ikas
    0.07
    å®ŀæĸ½æĿ¡ä¾ĭ
    0.07
    ¤íĭ
    0.07
    unday
    0.07
    æ¾Ħ
    0.07
    ritt
    0.07
    afort
    0.06
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.06
    __,__
    0.06
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    0.06
    Activations Density 0.332%

    No Known Activations