© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20709
    Prev
    Next
    INDEX
    Explanations

    Comments or example phrases

    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
    åµĮ
    -0.07
    ÑĦÑĸ
    -0.07
    å¾ĭ
    -0.07
    åı¯ä½ľä¸º
    -0.07
    paren
    -0.07
     paren
    -0.07
    полÑı
    -0.06
    èĻ½çĦ¶ä¸įæĺ¯
    -0.06
     agu
    -0.06
    ynd
    -0.06
    POSITIVE LOGITS
    .getById
    0.08
    主è¦ģ表çݰ为
    0.08
     пÑĢоÑı
    0.07
    çļĦå®ļä¹ī
    0.07
     manifest
    0.07
     distractions
    0.07
    otov
    0.07
    表çݰ为
    0.07
    ÙĪاء
    0.07
    Ø·Ùħ
    0.07
    Activations Density 0.002%

    No Known Activations