© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22190
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    aal
    -0.09
    .addHandler
    -0.09
    ê°ģ
    -0.08
    eer
    -0.08
    vas
    -0.08
     меÑģÑĤо
    -0.08
    kes
    -0.08
     prospects
    -0.08
    inate
    -0.08
    oby
    -0.08
    POSITIVE LOGITS
    æľ¬æĬ¥
    0.10
    ../../../
    0.10
    çļĦä¸Ģ项
    0.10
    æĪijå¿ĥéĩĮ
    0.10
    为äºĨéģ¿åħį
    0.09
    å¾Īéĩįè¦ģçļĦ
    0.09
    æĮ¯åħ´
    0.09
    çļĦçľ¼çĿĽ
    0.09
    æľįåĬ¡ä½ĵç³»
    0.09
    spir
    0.09
    Activations Density 0.037%

    No Known Activations