© 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. 42102
    Prev
    Next
    INDEX
    Explanations

    participation in

    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
    اء
    -0.08
    earing
    -0.07
    ician
    -0.07
    lendir
    -0.07
    arness
    -0.07
    eward
    -0.07
    enberg
    -0.07
    ically
    -0.07
    Äįku
    -0.07
    presso
    -0.06
    POSITIVE LOGITS
    ниÑĨÑĮ
    0.10
    èĢħåľ¨
    0.09
    icipation
    0.09
    èĢħçļĦ
    0.09
    ivity
    0.09
    è¿ĽæĿ¥
    0.09
    OrElse
    0.09
    itional
    0.09
    unj
    0.08
     pleinement
    0.08
    Activations Density 0.061%

    No Known Activations