© 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. 28877
    Prev
    Next
    INDEX
    Explanations

    numbers and special 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
    ingan
    -0.10
    chera
    -0.08
    ikin
    -0.08
    /gpl
    -0.08
    ialis
    -0.07
    olino
    -0.07
    fert
    -0.07
    ilon
    -0.07
    สุà¸Ķ
    -0.07
    ÑĤон
    -0.07
    POSITIVE LOGITS
    ly
    0.09
    osos
    0.08
    mond
    0.06
    undos
    0.06
    andy
    0.06
    EX
    0.06
    usst
    0.06
    åĬłå¾®ä¿¡
    0.06
     Palmer
    0.06
    emar
    0.06
    Activations Density 0.001%

    No Known Activations