© 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. 55376
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
    ÑĢим
    -0.07
    å¼ģ
    -0.07
    кÑĥлÑĮ
    -0.07
    åı¯æĥ³èĢĮçŁ¥
    -0.07
    abe
    -0.06
    å¦Ĥ对
    -0.06
    åĿŁå¢ĵ
    -0.06
     modifications
    -0.06
    å¦Ĥ
    -0.06
    å¦ĤåĽł
    -0.06
    POSITIVE LOGITS
    åıįè§Ĥ
    0.07
    engel
    0.07
    æĪĸèĢħæĺ¯
    0.07
    plus
    0.07
     Plus
    0.07
    Plus
    0.07
     whereas
    0.07
    kish
    0.07
     Amen
    0.07
    å¤ļä¸ĢäºĽ
    0.07
    Activations Density 0.014%

    No Known Activations