© 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. 31914
    Prev
    Next
    INDEX
    Explanations

    national followed by specific nouns

    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
    Ķ
    -0.07
    ราย
    -0.07
    å¹´åįİ
    -0.06
    illant
    -0.06
    à¸ģ
    -0.06
    ণ
    -0.06
    年头
    -0.06
    IGHT
    -0.06
    est
    -0.06
    oras
    -0.06
    POSITIVE LOGITS
    ized
    0.12
    ization
    0.11
    isation
    0.10
    à¥įरà¥Ģय
    0.10
    /reg
    0.10
    åĴĮçľģ
    0.09
    issimi
    0.09
    /local
    0.09
    izing
    0.09
    åĴĮåľ°æĸ¹
    0.09
    Activations Density 0.092%

    No Known Activations