© 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. 16555
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions relating variables

    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
    orado
    -0.07
    涵
    -0.07
    ¶
    -0.07
     flush
    -0.07
    زاÙħ
    -0.07
    flush
    -0.06
    à¸ģรา
    -0.06
     CancellationToken
    -0.06
    ×ij×ķר
    -0.06
    æĩĤå¾ĹäºĨ
    -0.06
    POSITIVE LOGITS
    å·¦åı³
    0.08
    лин
    0.07
    het
    0.07
    HOT
    0.07
    ØŃØ©
    0.07
    åīįåIJİ
    0.06
    schild
    0.06
    å¡
    0.06
    лÑĥ
    0.06
    ONES
    0.06
    Activations Density 0.002%

    No Known Activations