© 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. 42091
    Prev
    Next
    INDEX
    Explanations

    Stokes and related names/terms

    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
    ä¸įæĥĬ
    -0.09
    çĥĪçļĦ
    -0.08
     renta
    -0.08
    itude
    -0.08
    å®ļçļĦ
    -0.08
    itudini
    -0.08
    osen
    -0.07
    ìļ´ëį°
    -0.07
    alda
    -0.07
    amas
    -0.07
    POSITIVE LOGITS
    çļĦ
    0.08
    erman
    0.07
    ÑģÑı
    0.07
    æĪijåIJ¬
    0.07
    nya
    0.07
    ìĿĦ
    0.07
    wiki
    0.07
    Ùĩا
    0.06
     Chapman
    0.06
    ÑĦоÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations