© 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. 40434
    Prev
    Next
    INDEX
    Explanations

    shifting contents

    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
    <![
    -0.08
    allen
    -0.08
    addon
    -0.08
    hoek
    -0.08
    ยà¹Īà¸Ńย
    -0.08
    ieten
    -0.07
    лаÑģ
    -0.07
    culaire
    -0.07
    天çĽĸ
    -0.07
    訣
    -0.07
    POSITIVE LOGITS
    ilter
    0.08
     remaining
    0.08
     recal
    0.08
    åİŁå®ļ
    0.08
    çĽ¸å¯¹
    0.08
    åİŁæĿ¥çļĦ
    0.07
    åİŁæľīçļĦ
    0.07
    顺延
    0.07
    åİŁæľ¬
    0.07
    åİŁåħĪ
    0.07
    Activations Density 0.041%

    No Known Activations