© 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. 12366
    Prev
    Next
    INDEX
    Explanations

    next step or sequence

    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
    å¦ĤæĦı
    -0.08
    .ib
    -0.08
    عب
    -0.08
    áĥ®
    -0.08
    ISP
    -0.08
    iert
    -0.08
    UIL
    -0.08
    å·²äºİ
    -0.07
    ningar
    -0.07
    èī¯
    -0.07
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.28
    ä¸ĭä¸ĢæŃ¥
    0.28
     next
    0.26
    ä¸ĭä¸Ģ
    0.24
    next
    0.24
    æİ¥ä¸ĭæĿ¥
    0.22
    	next
    0.19
    -next
    0.19
     NEXT
    0.19
     nächsten
    0.19
    Activations Density 0.184%

    No Known Activations