© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46621
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming 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
    able
    -0.09
    ure
    -0.07
    ABLE
    -0.07
    uring
    -0.07
    ables
    -0.06
     Phá»ķ
    -0.06
    åºĨ
    -0.06
    诺
    -0.06
    ob
    -0.06
    jure
    -0.06
    POSITIVE LOGITS
    rias
    0.08
    à¹Īà¸Ńย
    0.07
    estig
    0.07
    âĤ¬âĦ¢
    0.07
    uilt
    0.07
    azer
    0.07
    ysh
    0.07
    ersp
    0.07
    yser
    0.07
    atici
    0.07
    Activations Density 0.013%

    No Known Activations