© 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. 30181
    Prev
    Next
    INDEX
    Explanations

    mixture of substances

    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
    ymp
    -0.09
    åħ¶èº«
    -0.08
    entifier
    -0.08
    ython
    -0.08
    åħ¶ä¸Ĭ
    -0.08
    mars
    -0.08
    imir
    -0.08
    idar
    -0.08
    ä¸įæ¸Ŀ
    -0.08
    bij
    -0.08
    POSITIVE LOGITS
    tures
    0.13
    à¸ľà¸ªà¸²à¸Ļ
    0.12
    er
    0.10
     halinde
    0.08
    ellaneous
    0.08
    osal
    0.08
    åľ¨ä¸Ģèµ·
    0.07
    ยà¹Īà¸Ńย
    0.07
    åĨµ
    0.07
    åIJĪçī©
    0.07
    Activations Density 0.008%

    No Known Activations