© 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. 18788
    Prev
    Next
    INDEX
    Explanations

    time expressions

    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
    éĢĤ
    -0.07
     count
    -0.07
    try
    -0.06
    باب
    -0.06
    éħįä¸Ĭ
    -0.06
    esson
    -0.06
    orra
    -0.06
    esi
    -0.06
    縮
    -0.06
    å°±æĽ´åĬł
    -0.06
    POSITIVE LOGITS
    ιÏĥÏĦα
    0.08
    olas
    0.08
    ãs
    0.08
    ׼×Ķ
    0.07
    онов
    0.07
    vet
    0.07
    ToDevice
    0.07
    endas
    0.07
    ouce
    0.07
    unge
    0.07
    Activations Density 0.002%

    No Known Activations