© 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. 57499
    Prev
    Next
    INDEX
    Explanations

    .Linq;

    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
    ä¸Ģ级
    -0.07
    ÙĪØ·
    -0.06
     pal
    -0.06
    æĭīæĭī
    -0.06
    ¦
    -0.06
     Zimmerman
    -0.06
    rane
    -0.06
    }$/
    -0.06
    пад
    -0.06
    ,NULL
    -0.06
    POSITIVE LOGITS
    å²³çĪ¶
    0.07
     заÑģе
    0.07
     Monten
    0.07
    èĩªæѤ
    0.07
    ikasi
    0.06
    èİĵ
    0.06
    ologne
    0.06
    eppe
    0.06
    ef
    0.06
    _extensions
    0.06
    Activations Density 0.344%

    No Known Activations