© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29670
    Prev
    Next
    INDEX
    Explanations

    horizontal rule character

    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
    Negative Logits
    ä¿ĿæĬ¤åĮº
    -0.10
    -0.09
    åĽ¾ä¹¦é¦Ĩ
    -0.09
    æĹłè®º
    -0.08
     spar
    -0.08
    ä¸į管æĺ¯
    -0.08
    ¼
    -0.08
    åĺ¤
    -0.08
    èı©æıIJ
    -0.08
    strap
    -0.08
    POSITIVE LOGITS
    dao
    0.11
    isser
    0.10
    ül
    0.09
     Dut
    0.09
    ASSERT
    0.09
    ì§ĵ
    0.09
    isc
    0.09
    ../../../
    0.09
    dr
    0.09
    esse
    0.08
    Activations Density 0.303%

    No Known Activations