© 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. 57782
    Prev
    Next
    INDEX
    Explanations

    non-english 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
    FFECT
    -0.08
    kent
    -0.08
    ÏĥÏĦε
    -0.08
    äºĮ级å¸Ĥåľº
    -0.08
    eree
    -0.08
    ÏįÏĦε
    -0.08
    esz
    -0.08
    ENDING
    -0.08
    antu
    -0.08
    esan
    -0.08
    POSITIVE LOGITS
    pc
    0.06
    č↵
    0.06
    omez
    0.06
    inar
    0.06
    ↵
    0.06
    ómez
    0.05
    он
    0.05
    ’
    0.05
    ê·¼
    0.05
     ↵
    0.05
    Activations Density 0.651%

    No Known Activations