© 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. 16802
    Prev
    Next
    INDEX
    Explanations

    current and future

    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¦ĤæľŁ
    -0.11
    尽管
    -0.09
    å°±æѤ
    -0.08
    oda
    -0.08
    çIJ°
    -0.08
    ä¸ĢåĪĩéĥ½
    -0.08
    çĶ°åĽŃ
    -0.08
    chains
    -0.08
    ä¸ŃåĽ½äººæ°ij
    -0.08
    å°±è¿Ļä¹Ī
    -0.08
    POSITIVE LOGITS
    å°ĨæĿ¥
    0.23
    æľªæĿ¥
    0.22
    åľ¨æľªæĿ¥
    0.21
     future
    0.19
    æľªæĿ¥çļĦ
    0.19
    .future
    0.18
    future
    0.18
    æľªæĿ¥åıijå±ķ
    0.17
    Future
    0.17
    æľªä¾Ĩ
    0.17
    Activations Density 0.105%

    No Known Activations