© 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. 40415
    Prev
    Next
    INDEX
    Explanations

    seal or connect

    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
    稿
    -0.10
    /pol
    -0.09
    panion
    -0.09
    ophilia
    -0.09
    çĶļä¹Ī
    -0.09
    èĭ¥å¹²
    -0.09
    æĹłéĻIJ
    -0.09
    SplitOptions
    -0.09
    ÅŁt
    -0.09
    IMO
    -0.08
    POSITIVE LOGITS
    éļĻ
    0.10
     seal
    0.09
    å¯Ĩå°ģ
    0.09
    æĪĺ
    0.09
     sealed
    0.09
    Leaks
    0.09
    ç½ħ
    0.09
    çī¢çī¢
    0.08
    æł¸åĩĨ
    0.08
     sealing
    0.08
    Activations Density 0.121%

    No Known Activations