© 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. 873
    Prev
    Next
    INDEX
    Explanations

    sell call, sell billions, sell before, sell securities, sell of

    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
    èįī
    -0.09
    çĶŁäº§ç»ıèIJ¥
    -0.09
    0
    -0.09
    翻身
    -0.08
    uv
    -0.08
    1
    -0.08
    4
    -0.08
    æĪijå¸ĮæľĽ
    -0.08
     Bever
    -0.08
    çĶŁæ´»ä¸Ń
    -0.08
    POSITIVE LOGITS
    åIJ¯ç¤º
    0.09
    iens
    0.09
     иÑģÑĤ
    0.09
    azel
    0.09
    åĴĢ
    0.09
    åĨ·åį´
    0.09
    åİĭåĬĽ
    0.09
    пон
    0.09
     Bought
    0.08
    åħ¬ä¸»
    0.08
    Activations Density 0.028%

    No Known Activations