© 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. 29545
    Prev
    Next
    INDEX
    Explanations

    No

    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
    äºĨåIJ§
    -0.09
    ender
    -0.08
    den
    -0.08
    ä¸įç»ıæĦı
    -0.08
    ston
    -0.08
    ounding
    -0.08
     Booker
    -0.08
    ayas
    -0.08
     somehow
    -0.08
    istol
    -0.08
    POSITIVE LOGITS
    zzle
    0.11
    è¢ľ
    0.10
    çĩĥ
    0.10
    ÂŃt
    0.10
    åĬ¼
    0.09
    ä¸İæŶ
    0.09
    ç»Łè®¡å±Ģ
    0.09
    atak
    0.09
    ÑģÑĤаÑĤ
    0.09
    ç§Ģ丽
    0.09
    Activations Density 0.113%

    No Known Activations