© 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. 60596
    Prev
    Next
    INDEX
    Explanations

    numbers ending with punctuation

    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
    °
    -0.07
    aira
    -0.07
    cket
    -0.07
    criptor
    -0.07
    amu
    -0.07
    porno
    -0.07
    çijľ
    -0.07
    integ
    -0.07
    odzi
    -0.07
    åĮł
    -0.07
    POSITIVE LOGITS
    ammers
    0.08
    ä¸įæŃ¢
    0.07
    авли
    0.07
    ä¹ĭå·ħ
    0.07
    yers
    0.07
    mond
    0.07
    é©°éªĭ
    0.07
    äº¤æĽ¿
    0.07
    èĦijçŃĭ
    0.07
    ecess
    0.06
    Activations Density 0.006%

    No Known Activations