© 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. 644
    Prev
    Next
    INDEX
    Explanations

    Black Knight

    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
    æĥħ人
    -0.10
     phoenix
    -0.09
    onest
    -0.09
    azon
    -0.09
    ä¸ĭå·´
    -0.09
    æı½
    -0.08
    åľ¨äº¬
    -0.08
    éĺ»åĬĽ
    -0.08
    neau
    -0.08
    obl
    -0.08
    POSITIVE LOGITS
    éĺ´
    0.10
     KEEP
    0.10
    kich
    0.09
    éĺ´éĺ³
    0.08
    æİĴ污
    0.08
     акÑĤÑĥ
    0.08
    åģ¥åħ¨
    0.08
    çķĻå®ĪåĦ¿ç«¥
    0.08
    æ·±å±Ĥ次
    0.08
    [array
    0.08
    Activations Density 0.145%

    No Known Activations