© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5373
    Prev
    Next
    INDEX
    Explanations

    unicode and related technical terms

    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
    éģĩ
    -0.10
    èѬ
    -0.10
    ä½ľé£İ
    -0.09
    çĸıéĢļ
    -0.09
     Grü
    -0.09
     Timber
    -0.08
    gio
    -0.08
    .translation
    -0.08
    åħ¥æĪ·
    -0.08
    声åĵį
    -0.08
    POSITIVE LOGITS
    楼å®ĩ
    0.10
     Unicode
    0.10
    _unicode
    0.09
    ç¾Į
    0.09
    ibus
    0.09
    æ¹Ľ
    0.09
    Unicode
    0.09
    é®
    0.09
    å°ijæķ°æ°ijæĹı
    0.09
    .Unicode
    0.09
    Activations Density 0.125%

    No Known Activations