© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    "all" or "others"

    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
    ebt
    -0.08
     Blasio
    -0.08
    <strong
    -0.08
    elman
    -0.08
    COMPARE
    -0.08
    ä¸Ģä¸įå°ıå¿ĥ
    -0.08
    zuh
    -0.07
    å¿ĺ
    -0.07
     sharply
    -0.07
    aign
    -0.07
    POSITIVE LOGITS
     comprehensive
    0.09
    æĽ´åħ¨éĿ¢
    0.09
    åĮħæĭ¬äºĨ
    0.09
     inclusive
    0.09
    涵çĽĸäºĨ
    0.09
    åĮħåIJ«äºĨ
    0.09
    åĮħ容
    0.08
     encompass
    0.08
    åħ¨éĿ¢çļĦ
    0.08
     umbrella
    0.08
    Activations Density 0.018%

    No Known Activations