© 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. 24534
    Prev
    Next
    INDEX
    Explanations

    actions after 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
    åĪĽå»ºäºİ
    -0.07
    ä¸įè¿ĩä»ĸ
    -0.07
    äºĶ大
    -0.07
    .static
    -0.07
    _TRY
    -0.07
    æīĢ以ä»ĸ
    -0.07
    lek
    -0.07
    עת
    -0.07
    PARSE
    -0.07
     yet
    -0.07
    POSITIVE LOGITS
     finally
    0.08
     tada
    0.07
    åĨįæİ¥
    0.07
    è¿Ļå°±æĺ¯
    0.07
    åį³ä¸º
    0.07
     VoilÃł
    0.07
     vigor
    0.07
     vigorously
    0.07
    tei
    0.07
    å®ĮäºĨ
    0.07
    Activations Density 0.110%

    No Known Activations