© 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. 12317
    Prev
    Next
    INDEX
    Explanations

    finally, lastly, etc

    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
    .dw
    -0.09
    /documentation
    -0.09
    erras
    -0.09
     ê²ĥìľ¼ë¡ľ
    -0.09
    Collector
    -0.09
    educt
    -0.08
    ê¹Į
    -0.08
    ä¼ļè§ģ
    -0.08
    åĽ½æľī
    -0.08
    éĶ¹
    -0.08
    POSITIVE LOGITS
    çŃīçŃī
    0.17
     finally
    0.15
     etc
    0.13
    	finally
    0.12
    etc
    0.12
    ç»Īäºİ
    0.12
    çı£
    0.12
    finally
    0.11
     Finally
    0.10
    Lastly
    0.10
    Activations Density 0.264%

    No Known Activations