© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    place names ending in lake, dale, or ington

    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
    æĪij说
    -0.09
    çģ«è½¦
    -0.08
    eto
    -0.08
    æĪijæĬĬ
    -0.08
    ãģĭãĤĬ
    -0.08
     Mits
    -0.07
    olf
    -0.07
    hä
    -0.07
    escape
    -0.07
    åı¯ä¿¡
    -0.07
    POSITIVE LOGITS
    è¹Ħ
    0.09
    æŁ¬
    0.09
    åIJĥäºĨ
    0.09
    ç¼Ģ
    0.09
    榫
    0.09
     обо
    0.09
    Dia
    0.09
    èĭ±æīį
    0.09
     nhắc
    0.09
    gift
    0.09
    Activations Density 0.031%

    No Known Activations