© 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. 3284
    Prev
    Next
    INDEX
    Explanations

    rigorous

    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
    æĽ´å¤ļ精彩åĨħ容
    -0.10
    баланÑģи
    -0.09
    éĩij森
    -0.09
    ñera
    -0.09
    stra
    -0.09
    egie
    -0.08
     INFORMA
    -0.08
    häl
    -0.08
    OrUpdate
    -0.08
    engah
    -0.08
    POSITIVE LOGITS
    严谨
    0.10
    -minded
    0.08
    yet
    0.08
    æľīæį®
    0.08
     yet
    0.07
    l
    0.07
     rigor
    0.07
    ạch
    0.07
     mathematical
    0.07
    èµ·è§ģ
    0.07
    Activations Density 0.004%

    No Known Activations