© 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. 60831
    Prev
    Next
    INDEX
    Explanations

    hit, struck, battered

    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
    ood
    -0.09
     Paz
    -0.09
    缴éĢļ车
    -0.08
    dling
    -0.08
    eners
    -0.08
    å©¢
    -0.08
    akan
    -0.08
    achel
    -0.08
    è§ĦåĪĻ
    -0.08
    磼
    -0.08
    POSITIVE LOGITS
    åīįåĪĹ
    0.11
    æķ´ä¸ª
    0.10
    æķ´åĢĭ
    0.09
     اÙĦبÙĦاد
    0.09
    hap
    0.09
    çĪĨåıij
    0.09
    åIJĦ个æĸ¹éĿ¢
    0.09
    ä¸ĸçķĮåIJĦåľ°
    0.09
    èĢĹ
    0.09
    åħ¬å¼Ģåıij
    0.09
    Activations Density 0.047%

    No Known Activations