© 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. 60902
    Prev
    Next
    INDEX
    Explanations

    odds winner, me out

    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
    Not in Any Lists

    No Comments

    Negative Logits
    etro
    -0.09
    ળ
    -0.09
    çĿĢä»ĸ
    -0.09
     Gaut
    -0.09
    ç£ĭåķĨ
    -0.09
     Ùħؤ
    -0.08
    èµ°ç§ģ
    -0.08
    æĪªåĽ¾
    -0.08
    è®®äºĭ
    -0.08
    çĤ¼
    -0.08
    POSITIVE LOGITS
    çľĭ好
    0.12
    æľŁæľĽ
    0.09
    åľ¨å¤ĸ
    0.09
    anko
    0.09
    çĽ¸å¯¹è¾ĥ
    0.09
     slim
    0.08
    æĸ°å½¢åĬ¿
    0.08
    ảng
    0.08
    æĤ¬å¿µ
    0.08
    åħ¬æĬ¥
    0.08
    Activations Density 0.215%

    No Known Activations