© 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. 45810
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation followed by common words

    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
    abis
    -0.08
     BÃģ
    -0.08
    åį³çĶ¨
    -0.07
    rens
    -0.07
    resp
    -0.07
    Ø®ÙĨ
    -0.07
    intang
    -0.07
    ahn
    -0.07
    .tif
    -0.07
    ä¹ĺ
    -0.06
    POSITIVE LOGITS
    æIJŃ
    0.08
     اصط
    0.07
     va
    0.07
    heid
    0.07
    å¡«åħ¥
    0.06
    itut
    0.06
    ogy
    0.06
    à¸Ĺิà¸Ļ
    0.06
    umen
    0.06
    两个åŃĹ
    0.06
    Activations Density 0.056%

    No Known Activations