© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21114
    Prev
    Next
    INDEX
    Explanations

    Australian Capital Territory, Labrador, Brunswick

    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
    æįķ
    -0.09
    ìĤ¬ìĹħ
    -0.09
    é£İæĻ¯åĮº
    -0.08
    æķ´æĶ¹
    -0.08
    èĪªæµ·
    -0.08
    ä¾®
    -0.08
    zap
    -0.08
    Mt
    -0.08
    .fromCharCode
    -0.08
    串
    -0.08
    POSITIVE LOGITS
    ç£Ļ
    0.10
    éļı
    0.09
    ä¼ļåIJĮ
    0.09
    æŃĨ
    0.08
    .www
    0.08
    æĦ¿
    0.08
    gü
    0.08
    chi
    0.08
    æĸ¹åı¯
    0.08
    ean
    0.08
    Activations Density 0.010%

    No Known Activations