© 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. 25860
    Prev
    Next
    INDEX
    Explanations

    superlative or extreme selection

    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
    stry
    -0.08
    eways
    -0.08
    íĭĢ
    -0.08
    åħ±è¿Ľ
    -0.08
    å°ı天
    -0.08
    enstein
    -0.08
    èľľæľĪ
    -0.08
     chÄĥng
    -0.08
    .setColumns
    -0.08
     compag
    -0.08
    POSITIVE LOGITS
    åĴĮæľĢ
    0.13
    /max
    0.10
     Selection
    0.10
     selection
    0.09
    ä¹Łæĺ¯æľĢ
    0.09
    Selection
    0.08
    selection
    0.08
    imum
    0.08
     among
    0.07
    riority
    0.07
    Activations Density 0.150%

    No Known Activations