© 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. 8488
    Prev
    Next
    INDEX
    Explanations

    rate bounds and convergence

    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
    æľĢçĥŃ
    -0.09
    è¿Ļç§į人
    -0.09
    reja
    -0.09
    abaya
    -0.09
    主èIJ¥äº§åĵģ
    -0.09
    çĤ¹åĩ»æŁ¥çľĭçŃĶæ¡Ī
    -0.08
    leton
    -0.08
     thinly
    -0.08
     recons
    -0.08
    abay
    -0.08
    POSITIVE LOGITS
     achieved
    0.08
    çŃī级
    0.07
    anny
    0.07
     improvement
    0.07
     degradation
    0.06
    uder
    0.06
     Corm
    0.06
    èIJ½èĬ±
    0.06
    ç²Ĺ
    0.06
    edis
    0.06
    Activations Density 0.009%

    No Known Activations