© 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. 841
    Prev
    Next
    INDEX
    Explanations

    funding opportunity announcement

    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
    èĩªåѦ
    -0.08
    çı§
    -0.08
    æĬ±
    -0.08
    å¤ĸæĿ¥
    -0.08
     ott
    -0.08
     Ñĥни
    -0.08
    ott
    -0.08
    èĽ©
    -0.08
     ACS
    -0.08
    åŀĮ
    -0.08
    POSITIVE LOGITS
    åIJįé¢Ŀ
    0.14
    çĶ³è¯·
    0.13
    çĶ³æĬ¥
    0.13
    ç«ŀäºī
    0.12
    çĶ³è¯·äºº
    0.12
    符åIJĪæĿ¡ä»¶
    0.11
    è¯Ħ审
    0.11
    çļĦç«ŀäºī
    0.11
     applicants
    0.11
    åŃª
    0.10
    Activations Density 0.068%

    No Known Activations