© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17955
    Prev
    Next
    INDEX
    Explanations

    .com, Copyright, officials

    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
    ¶ļ
    -0.08
    ometown
    -0.07
    ลัà¸ļ
    -0.07
    糯
    -0.07
    _restart
    -0.07
    adra
    -0.07
    è¿Ļ个社ä¼ļ
    -0.07
    arpa
    -0.07
    åĴĮä¸įèī¯
    -0.07
    DEV
    -0.07
    POSITIVE LOGITS
    egrity
    0.06
    åĽ½å®¶æłĩåĩĨ
    0.06
    pd
    0.06
    вÑĸв
    0.06
     itself
    0.05
    اÙģ
    0.05
     خبر
    0.05
    ccio
    0.05
     impar
    0.05
    plom
    0.05
    Activations Density 1.203%

    No Known Activations