© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52572
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers in sports contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İå°ıå°±
    -0.10
    .enterprise
    -0.10
    橱
    -0.09
    شؤ
    -0.09
    æijĩ
    -0.09
    åįĥåı¤
    -0.09
    éĬ®
    -0.09
    éªĪ
    -0.09
    ordo
    -0.09
    æĬĬæĮģ
    -0.09
    POSITIVE LOGITS
    æĸ°åĨľæĿij
    0.09
    nish
    0.08
    ë§Ŀ
    0.08
    ฯ
    0.08
    åįĪ
    0.07
    CLR
    0.07
    å¤ĸåĽ½äºº
    0.07
    LOB
    0.07
    2
    0.07
    ÑĦÑĦ
    0.07
    Activations Density 0.004%

    No Known Activations