© 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. 25748
    Prev
    Next
    INDEX
    Explanations

    regex anchors and metacharacters

    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
    éĻį
    -0.07
    ÑĢем
    -0.07
    éªĮ
    -0.07
    elmet
    -0.07
    paralle
    -0.06
     Isaac
    -0.06
    éģ®
    -0.06
     manifests
    -0.06
    åIJįä¹ī
    -0.06
    Vit
    -0.06
    POSITIVE LOGITS
    符
    0.09
    éĻIJå®ļ
    0.08
     flexib
    0.08
     restrictive
    0.07
    à¸ģุล
    0.07
     scope
    0.07
    å¸ĮæľĽåľ¨
    0.07
    bourg
    0.07
     greed
    0.07
    flex
    0.07
    Activations Density 0.073%

    No Known Activations