© 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. 777
    Prev
    Next
    INDEX
    Explanations

    an a

    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
    次è¦ģ
    -0.10
    èĩĨ
    -0.10
    åīįèĢħ
    -0.09
    åĩĨç¡®æĢ§
    -0.09
    åıijçİ°éĹ®é¢ĺ
    -0.09
    unal
    -0.09
    ikel
    -0.09
    CLS
    -0.09
    éªł
    -0.09
    åijĶ
    -0.09
    POSITIVE LOGITS
    å°±è¿Ļæł·
    0.09
    ä¸Ģ家
    0.09
     “
    0.08
    ä¸Ģç«Ļå¼ı
    0.08
    ä¸İæѤ
    0.08
    åħ±èµ¢
    0.08
     warp
    0.08
    绣ä¸Ģ
    0.08
    ä¸Ģå¼ł
    0.08
    æĸ°çļĦ
    0.08
    Activations Density 0.294%

    No Known Activations