© 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. 9474
    Prev
    Next
    INDEX
    Explanations

    out or timeout

    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
    è¾Ł
    -0.10
    åıªåī©ä¸ĭ
    -0.09
    pres
    -0.09
    æѤæ¡Ī
    -0.08
    lage
    -0.08
    ments
    -0.08
    instr
    -0.08
    زاد
    -0.08
    ongo
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    POSITIVE LOGITS
    æĮĪ
    0.09
    _Internal
    0.09
    éļħ
    0.08
     ÑĪиÑĢоко
    0.08
    ÑĤоп
    0.08
    andy
    0.08
    å¿ĥçģµ
    0.08
    unc
    0.08
     пиÑĤ
    0.08
    ä½ĵ积
    0.08
    Activations Density 0.003%

    No Known Activations