© 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. 45924
    Prev
    Next
    INDEX
    Explanations

    numbers after symbols or words

    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
    elson
    -0.08
    iterate
    -0.07
     vla
    -0.06
    utex
    -0.06
     alternatively
    -0.06
    åĬŁäºİ
    -0.06
    rawn
    -0.06
    ZION
    -0.06
    ajari
    -0.06
    人影
    -0.06
    POSITIVE LOGITS
    à¹Ĩ
    0.09
    à¹Ħหà¸Ļ
    0.09
    à¹ĥà¸Ķ
    0.08
     à¹Ĩ
    0.08
    à¹Ģà¸Ķียว
    0.08
    ones
    0.07
    à¸Ĭาà¸ķิ
    0.07
    à¸Ļัà¹īà¸Ļ
    0.07
    ieties
    0.07
    ewnÄĻ
    0.07
    Activations Density 0.067%

    No Known Activations