© 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. 42434
    Prev
    Next
    INDEX
    Explanations

    MRI

    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
    gether
    -0.14
    à§įত
    -0.11
    ../../
    -0.10
    ting
    -0.10
    Ø©
    -0.09
    е
    -0.08
    abouts
    -0.08
    ation
    -0.08
    eness
    -0.07
    ت
    -0.07
    POSITIVE LOGITS
    ãĥ³
    0.10
    sing
    0.09
    ergestellt
    0.09
    ¹
    0.08
    agini
    0.08
    schen
    0.08
    æ¼ĶçļĦ
    0.08
    çĽ¸ä¼¼æĸĩçĮ®
    0.08
    kland
    0.07
    sprach
    0.07
    Activations Density 0.002%

    No Known Activations