© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    chance to or 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
    Negative Logits
    æĹłæīĢ
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.09
    ç»ĻäºĨæĪij
    -0.09
    ç®Ń
    -0.09
    ALLE
    -0.09
    ways
    -0.09
    éĹ®æĪij
    -0.09
    åĬĪ
    -0.09
    ihar
    -0.08
    æľīç§į
    -0.08
    POSITIVE LOGITS
    éļ¾å¾Ĺ
    0.10
    箫
    0.09
    antino
    0.09
    ÑĢÑı
    0.09
    æĬĦ
    0.09
    GetProperty
    0.09
    åħ¼
    0.08
     Ñĥзн
    0.08
     Knight
    0.08
    广大
    0.08
    Activations Density 0.016%

    No Known Activations