© 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. 58555
    Prev
    Next
    INDEX
    Explanations

    using System

    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¸Ĭä¸į
    -0.07
    kte
    -0.07
    cule
    -0.07
    n
    -0.07
    大ä¼ļåłĤ
    -0.06
    ancier
    -0.06
    nade
    -0.06
    ä¸įè°ĥ
    -0.06
    endra
    -0.06
    á»ĵng
    -0.06
    POSITIVE LOGITS
    REEN
    0.09
     keny
    0.08
    ysi
    0.07
    port
    0.07
    ัà¹Īà¸Ļ
    0.07
    ä¹ħçļĦ
    0.07
    pos
    0.07
    áĢ·
    0.06
    cest
    0.06
    è¯į
    0.06
    Activations Density 0.110%

    No Known Activations