© 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. 15840
    Prev
    Next
    INDEX
    Explanations

    minimum cut graph

    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
    NullOr
    -0.08
    isel
    -0.08
    ouri
    -0.08
    zet
    -0.07
    apan
    -0.07
    lical
    -0.07
    åIJĴ
    -0.07
    odat
    -0.07
    飻
    -0.07
    sole
    -0.07
    POSITIVE LOGITS
    è¦ĨçĽĸ
    0.08
     DeV
    0.07
     clique
    0.07
    æľĢå°ı
    0.07
    åī²
    0.07
     minimum
    0.07
    antu
    0.07
     Coloring
    0.06
     Minimum
    0.06
    èļģ
    0.06
    Activations Density 0.006%

    No Known Activations