© 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. 63256
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    -même
    -0.07
    OrUpdate
    -0.07
    reen
    -0.07
    igan
    -0.07
    ennes
    -0.07
    лее
    -0.07
    паÑĢÑĤа
    -0.07
    uild
    -0.07
    builder
    -0.07
    bies
    -0.07
    POSITIVE LOGITS
     punctuation
    0.08
    jik
    0.07
     punc
    0.07
    å¦ĤæŃĮ
    0.07
    Trail
    0.07
    é¡ŀ
    0.07
     бог
    0.07
    elsea
    0.07
    ph
    0.07
    unctuation
    0.07
    Activations Density 0.005%

    No Known Activations