© 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. 63738
    Prev
    Next
    INDEX
    Explanations

    use for

    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
    ijn
    -0.09
    æīĺ
    -0.09
    éķIJ
    -0.08
     Adler
    -0.08
    meld
    -0.08
    æªĢ
    -0.08
    æľīçĶ¨çļĦ
    -0.08
    åįıåIJĮåıijå±ķ
    -0.08
     Walters
    -0.07
    -parts
    -0.07
    POSITIVE LOGITS
    éĽ¾
    0.09
    å¥Ī
    0.09
    aN
    0.09
    åħ¬è®¤
    0.09
    Diamond
    0.09
    alom
    0.09
     пÑĥÑĤ
    0.09
    触
    0.09
    дов
    0.09
    ãģĭãģªãģĦ
    0.09
    Activations Density 0.047%

    No Known Activations