© 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. 30868
    Prev
    Next
    INDEX
    Explanations

    article or passage content

    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
    ק×ķת
    -0.09
    éĶ¦æ¶Ľ
    -0.08
    æĸ¹éĿ¢æľī
    -0.08
    arczy
    -0.08
    lement
    -0.08
    onsel
    -0.08
    åIJIJåĩº
    -0.07
    æĸ¹éĿ¢
    -0.07
    lements
    -0.07
    çĽ´ç³»
    -0.07
    POSITIVE LOGITS
    å¼Ģ头
    0.09
    çŁŃæĸĩ
    0.08
    段èIJ½
    0.08
     paragraphs
    0.08
     paragraph
    0.08
    讲述
    0.08
    æĿIJæĸĻ
    0.07
     material
    0.07
    çIJ¦
    0.07
    ä¸Ńæµ·
    0.07
    Activations Density 0.022%

    No Known Activations