© 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. 8326
    Prev
    Next
    INDEX
    Explanations

    scientific or abstract 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
    uned
    -0.10
    _Util
    -0.09
     Burns
    -0.09
    è¢Ĵ
    -0.09
    ä¸Ģçĵ¶
    -0.09
    uslim
    -0.09
    è¿ĻåIJį
    -0.09
    utar
    -0.09
    åįİ侨
    -0.09
    æ²¹èĢĹ
    -0.09
    POSITIVE LOGITS
    ä¸ĭéĻį
    0.09
    oul
    0.09
    -san
    0.08
    产ä¸ļåıijå±ķ
    0.08
    ardy
    0.08
    dig
    0.08
    æ¯ıå¹´éĥ½
    0.08
    rna
    0.08
    éŀŃ
    0.08
    ä¸ĭä¸Ģ个
    0.08
    Activations Density 0.028%

    No Known Activations