© 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. 51903
    Prev
    Next
    INDEX
    Explanations

    after

    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
    åĩıåħį
    -0.10
    otel
    -0.09
    å±ıèĶ½
    -0.09
    evin
    -0.08
    istar
    -0.08
    æĶ¾åѦ
    -0.08
    è·ŁæĪij
    -0.08
    äºĭæĥħ
    -0.08
    é©´
    -0.08
    heimer
    -0.08
    POSITIVE LOGITS
    /std
    0.08
    æľĢåIJİä¸Ģ个
    0.08
    å°ļæľª
    0.08
    æľĢåIJİä¸Ģ
    0.08
    æĹłéĻIJ
    0.08
    æ¯ķç«Łæĺ¯
    0.08
    ä»ŀ
    0.08
    ãĤıãģļ
    0.08
    åħ±åĪĽ
    0.08
    yro
    0.08
    Activations Density 0.031%

    No Known Activations