© 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. 21056
    Prev
    Next
    INDEX
    Explanations

    for which

    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
    è¯Ŀ说
    -0.11
    éĴĬ
    -0.10
    æĬ»
    -0.09
    åģ¥åº·çļĦ
    -0.09
    ä»İæł¹æľ¬
    -0.09
    并ä¸įæĦıåij³
    -0.09
    çĽĺæ´»
    -0.09
    æĬĵ好
    -0.09
    dig
    -0.09
    ä¸īæľŁ
    -0.09
    POSITIVE LOGITS
    adt
    0.10
    altung
    0.09
    æij©æĵ¦
    0.09
    /how
    0.09
    itel
    0.08
    ìķĹ
    0.08
    å¥ĭæĸĹ
    0.08
    HOOK
    0.08
    rips
    0.08
    bras
    0.08
    Activations Density 0.037%

    No Known Activations