© 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. 29373
    Prev
    Next
    INDEX
    Explanations

    import {, useEffect, useState, Component

    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
    综åIJĪæľįåĬ¡
    -0.08
    ntag
    -0.07
    /layouts
    -0.07
    iegel
    -0.07
    sockopt
    -0.07
    OwnProperty
    -0.07
    á»ħn
    -0.07
    ór
    -0.07
    ankan
    -0.07
    så
    -0.07
    POSITIVE LOGITS
     ãĢģ
    0.07
     volupt
    0.06
    çĨŁ
    0.06
    家å®Ŀ
    0.06
    çĨŁçļĦ
    0.06
    çīµ
    0.06
     Mend
    0.06
    duit
    0.06
    ï¼īãĢģ
    0.06
    Gener
    0.06
    Activations Density 0.005%

    No Known Activations