© 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. 24196
    Prev
    Next
    INDEX
    Explanations

    TD to passes

    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
    轸
    -0.09
    æĶ¾å®½
    -0.09
     ÑįÑĤап
    -0.09
    uzzi
    -0.09
    åĪĨæł¡
    -0.09
     TestUtils
    -0.09
    çŁ¥åIJį度
    -0.09
    å³°åĢ¼
    -0.09
    çĥĽ
    -0.09
    æĬ¥ä¸ļ
    -0.09
    POSITIVE LOGITS
    æī£
    0.09
    -ever
    0.08
    OVE
    0.08
    åıªèĥ½
    0.08
    иÑģк
    0.08
    ve
    0.08
    appoint
    0.08
     Braun
    0.08
    omba
    0.08
    æĺ¯æľĢ好çļĦ
    0.08
    Activations Density 0.001%

    No Known Activations