© 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. 9329
    Prev
    Next
    INDEX
    Explanations

    bluefin tuna, American toads, red shiners, harp seals, dolphins, silky anteaters, herring gulls, green-legged partridge

    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
    erset
    -0.10
    ç¼Ģ
    -0.09
    ä¸ĩåĪĨ
    -0.09
    ç¥Ń
    -0.09
    èĬ±å¼Ģ
    -0.09
    å¢ĵ
    -0.09
    åĸĿæ°´
    -0.09
    _gradients
    -0.09
    çļĦæ°Ķæģ¯
    -0.08
     enumerator
    -0.08
    POSITIVE LOGITS
    dest
    0.10
    blem
    0.10
     DEST
    0.09
     اÙĦعÙħ
    0.09
     Sus
    0.09
    翱
    0.09
     Lesser
    0.09
    æľīæľŁ
    0.09
    DEST
    0.09
    她说
    0.08
    Activations Density 0.072%

    No Known Activations