© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign characters

    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
    tures
    -0.15
    edException
    -0.11
    tedir
    -0.10
    ness
    -0.10
    ยà¸Ļà¸ķรà¹Į
    -0.10
    äºĨæĮĩ
    -0.10
    èĢħåľ¨
    -0.10
    ificates
    -0.09
    quiera
    -0.09
    anced
    -0.09
    POSITIVE LOGITS
    Ùĩ
    0.21
    ãĥ³
    0.20
    ly
    0.13
    u
    0.13
    ed
    0.13
    åĴĮ
    0.13
    çļĦ
    0.12
    ×ķ
    0.12
    o
    0.12
    åľ¨
    0.12
    Activations Density 0.004%

    No Known Activations