© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    ema
    -0.08
    ãģĸãĤĭ
    -0.07
    oler
    -0.07
    ä¸ĭ端
    -0.07
    éĩijé¦Ļ
    -0.07
    ordinate
    -0.06
    PROP
    -0.06
    idth
    -0.06
    .squeeze
    -0.06
    (Calendar
    -0.06
    POSITIVE LOGITS
     ÙħجÙħÙĪع
    0.09
    addAll
    0.09
     sums
    0.08
    对称
    0.08
    åįģäºĮæĿ¡
    0.08
     symmetric
    0.08
     symmetry
    0.08
     pairwise
    0.08
    .addAll
    0.07
     equality
    0.07
    Activations Density 0.004%

    No Known Activations