© 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. 26675
    Prev
    Next
    INDEX
    Explanations

    recurrence after

    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
    iglio
    -0.07
    ÙĪÙĦÙī
    -0.07
    åı¦å¤ĸä¸Ģç§į
    -0.07
    ocator
    -0.07
    سÙħ
    -0.07
    伺åĢĻ
    -0.07
    ä¿Ŀå§Ĩ
    -0.07
     пÑĢÑıм
    -0.07
    åī©ä½Ļ
    -0.07
    ui
    -0.06
    POSITIVE LOGITS
     thereof
    0.11
    ability
    0.08
    æĢ§å¥½
    0.08
    iability
    0.07
    lex
    0.07
    èĮģ
    0.07
    orex
    0.07
    ENV
    0.07
    ake
    0.06
     évent
    0.06
    Activations Density 0.257%

    No Known Activations