© 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. 43274
    Prev
    Next
    INDEX
    Explanations

    consecutive numbers or qualitative assessments

    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
    adera
    -0.08
     بع
    -0.08
    åĽŀé¦ĸ
    -0.07
    à´³àµį
    -0.07
     comp
    -0.07
    amol
    -0.07
    fl
    -0.07
    à¸Ńà¹Ģร
    -0.07
    opin
    -0.07
    ൾ
    -0.07
    POSITIVE LOGITS
     |[
    0.07
    ISP
    0.07
    æķĻç§ijæĸĩ
    0.06
    ellan
    0.06
    ensburg
    0.06
    .getWriter
    0.06
    bst
    0.06
    é«ĺé«ĺ
    0.06
    обо
    0.06
    ئÙĦ
    0.06
    Activations Density 0.001%

    No Known Activations