© 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. 60795
    Prev
    Next
    INDEX
    Explanations

    only want

    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
    éģµå®Ī
    -0.09
    æĮīæŶ
    -0.09
    è·Įçł´
    -0.08
    å°±å¤Ł
    -0.08
    修为
    -0.08
    说åĪ°è¿ĻéĩĮ
    -0.08
    adge
    -0.08
    enberg
    -0.08
    å¦ĤæľŁ
    -0.07
    olders
    -0.07
    POSITIVE LOGITS
    æĥ³è¦ģ
    0.24
     ingin
    0.21
    å¸ĮæľĽèĥ½å¤Ł
    0.21
     muá»ijn
    0.21
    å¸ĮæľĽéĢļè¿ĩ
    0.20
    æĥ³çŁ¥éģĵ
    0.20
    å¸ĮæľĽ
    0.19
    æĥ³æī¾
    0.19
     want
    0.19
    å¸ĮæľĽèĥ½
    0.19
    Activations Density 0.294%

    No Known Activations