© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    geometric shapes, ASCII numbers, arch analysis

    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
    resco
    -0.08
    æĺĬ天
    -0.08
    imers
    -0.07
    otra
    -0.07
    جرة
    -0.07
    attoo
    -0.07
     Summers
    -0.07
    again
    -0.07
    ecto
    -0.07
    .catch
    -0.07
    POSITIVE LOGITS
    ÙĬØ«
    0.07
    -val
    0.07
    æĬķèµĦ人
    0.06
    ç»´å¥ĩ
    0.06
    å¦ĩ
    0.06
    人
    0.06
    ãĥĶãĥ³
    0.06
    æľµæľµ
    0.06
    пеÑĨ
    0.06
    thic
    0.06
    Activations Density 0.012%

    No Known Activations