© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2857
    Prev
    Next
    INDEX
    Explanations

    foreign language prefixes and suffixes

    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
    loomberg
    -0.07
    èº
    -0.07
    .mozilla
    -0.07
    æĹłåıĮ
    -0.06
    à¨ħ
    -0.06
    itier
    -0.06
     disproportionately
    -0.06
    :auto
    -0.06
     punc
    -0.06
    parable
    -0.06
    POSITIVE LOGITS
    yme
    0.07
    edor
    0.07
    屿
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    ä¸Ńå¤ĸ
    0.07
    <|fim_suffix|>
    0.07
    alli
    0.07
    avers
    0.07
    以ä¸ĬåѦåİĨ
    0.07
    abe
    0.07
    Activations Density 0.420%

    No Known Activations