© 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. 36787
    Prev
    Next
    INDEX
    Explanations

    Flipboard, board, Pixel

    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
    .returnValue
    -0.09
    eil
    -0.09
    åĨ¥
    -0.09
    _ASM
    -0.09
    绸
    -0.09
    ä¸ĢæĹ¥
    -0.09
    åĴĮæľįåĬ¡
    -0.09
    ourd
    -0.08
    æłı
    -0.08
    å¾·å°Ķ
    -0.08
    POSITIVE LOGITS
    累累
    0.09
    æģIJæħĮ
    0.08
    éģĴ
    0.08
     rá»iji
    0.08
    onal
    0.08
     Äijá»ģ
    0.08
    elan
    0.08
    uz
    0.08
    å¼Ľ
    0.08
    亥
    0.08
    Activations Density 0.016%

    No Known Activations