© 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. 26183
    Prev
    Next
    INDEX
    Explanations

    universe and canon lore

    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
    èīº
    -0.09
    çľĭä¸Ĭåİ»
    -0.09
    èī¯
    -0.09
    å©´
    -0.09
    央
    -0.08
    èĹĿ
    -0.08
    è¯Ī
    -0.08
    otron
    -0.08
     repet
    -0.08
     innoc
    -0.08
    POSITIVE LOGITS
     canon
    0.10
    åī§æĥħ
    0.10
    å®ĺæĸ¹
    0.10
    åİŁèijĹ
    0.09
    ä¸ĸçķĮè§Ĥ
    0.09
    verse
    0.09
    æ·¡
    0.09
    lore
    0.09
    伤åı£
    0.09
     Official
    0.09
    Activations Density 0.159%

    No Known Activations