© 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. 41473
    Prev
    Next
    INDEX
    Explanations

    worst-case analysis and robust estimation

    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
    onga
    -0.07
    _FMT
    -0.07
    æĶ¹éĿ©åĪĽæĸ°
    -0.07
    åĪĽæĸ°
    -0.07
    derung
    -0.07
    WithValue
    -0.07
    åįĹåĮĹ
    -0.06
     Entw
    -0.06
    .ly
    -0.06
    rief
    -0.06
    POSITIVE LOGITS
     worst
    0.15
     Worst
    0.12
     worse
    0.10
     ìµľìķħ
    0.09
     advers
    0.09
    wor
    0.09
    æľĢå·®
    0.09
    æľĢä¸į
    0.09
    æŀģ端
    0.08
     pessim
    0.08
    Activations Density 0.010%

    No Known Activations