© 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. 12892
    Prev
    Next
    INDEX
    Explanations

    domains and company names

    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
    -0.09
    Ø©
    -0.08
    entication
    -0.07
    ugin
    -0.07
    ÙĦب
    -0.07
    -même
    -0.07
    wards
    -0.07
    uates
    -0.07
    zeug
    -0.07
    ç¼¥
    -0.07
    POSITIVE LOGITS
    .fasterxml
    0.12
    panion
    0.11
    ercial
    0.11
     gái
    0.11
    .baomidou
    0.10
    er
    0.10
    mercial
    0.10
    .squareup
    0.10
    .googlecode
    0.10
     dál
    0.09
    Activations Density 0.228%

    No Known Activations