© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55465
    Prev
    Next
    INDEX
    Explanations

    vintage, classic, historic, old, antique

    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
    å½ĵæŶçļĦ
    -0.12
    éĤ£ä¸ªæŶåĢĻ
    -0.10
    ducted
    -0.09
    andi
    -0.09
     ëĭ¹ìĭľ
    -0.09
    éĤ£æŶ
    -0.08
    -os
    -0.08
    itor
    -0.08
    æĹ¶ä»£çļĦ
    -0.08
    ayer
    -0.08
    POSITIVE LOGITS
    -established
    0.10
    使人
    0.09
    èĢģå®ŀ
    0.09
     пен
    0.09
    enburg
    0.08
    æij¸
    0.08
    zzle
    0.08
     Gem
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    æĭ·
    0.08
    Activations Density 0.131%

    No Known Activations