© 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. 6217
    Prev
    Next
    INDEX
    Explanations

    on or up

    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
    å¼ķ
    -0.10
    ç»ıæµİä½ĵ
    -0.09
     RETURNS
    -0.08
    ä¾µ
    -0.08
    aat
    -0.08
    ubi
    -0.08
    çĹķ
    -0.08
    èĦijæµ·ä¸Ń
    -0.08
    HttpRequest
    -0.07
    ÃŃnh
    -0.07
    POSITIVE LOGITS
    ibal
    0.10
     Presidents
    0.09
    iston
    0.09
    æĥħæĢĢ
    0.09
    ục
    0.09
    åѦä¼ļäºĨ
    0.09
    æī¹åĩĨ
    0.09
    å³¥
    0.08
    :`~
    0.08
    æ®Ĥ
    0.08
    Activations Density 0.015%

    No Known Activations