© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    English language specifications

    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
    åģļåĪ°
    -0.10
    è¿ĩæĿ¥
    -0.09
    æ±ľ
    -0.09
     likewise
    -0.09
    롤
    -0.09
    abor
    -0.08
    ãģ¾ãģĹãģ¦
    -0.08
    æĸ¹ãģ¯
    -0.08
     Pit
    -0.08
    esson
    -0.08
    POSITIVE LOGITS
    æłĬ
    0.09
    æĨĶ
    0.09
    EPS
    0.08
    为åĩĨ
    0.08
    为主
    0.08
    åıĬ缸åħ³
    0.08
    ä¸Ģæľµ
    0.08
    æľ¬è´¨ä¸Ĭ
    0.08
    äºĨäºĽ
    0.08
    alyzed
    0.08
    Activations Density 0.482%

    No Known Activations