© 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. 33663
    Prev
    Next
    INDEX
    Explanations

    import pandas as pd

    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
     Hud
    -0.07
    OwnProperty
    -0.07
    ä¸ļåįıä¼ļ
    -0.07
    uret
    -0.07
    ero
    -0.07
    pod
    -0.07
    inyin
    -0.07
     Sido
    -0.06
    stown
    -0.06
    åı¦ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    zien
    0.08
    çĶ³æĺİ
    0.07
    adays
    0.07
    åĨįä¹Łä¸į
    0.07
    æĬĬ好
    0.07
    etlen
    0.07
    å¿ĥäºĨ
    0.06
    å¤ĸçľģ
    0.06
    esti
    0.06
    evo
    0.06
    Activations Density 0.011%

    No Known Activations