© 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. 27447
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    积èĵĦ
    -0.09
    è¶Ĭæĺ¯
    -0.09
    è¦ģåģļ好
    -0.09
    èĵĦ
    -0.09
    åħ¶ä»ĸçļĦ
    -0.09
     ÑĢанее
    -0.09
    æĢ§æł¼
    -0.08
     Scarlet
    -0.08
    读æĩĤ
    -0.08
     lite
    -0.08
    POSITIVE LOGITS
     either
    0.09
    haven
    0.09
     now
    0.09
    æħ°
    0.09
    çļĦæĶ¯æĮģ
    0.09
    avin
    0.08
    çĽ´è¾¾
    0.08
    æĸ½è¡Į
    0.08
     Aquarium
    0.08
    ared
    0.08
    Activations Density 0.213%

    No Known Activations