© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    Romeo and Juliet specific names

    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
    åĸľæ¬¢
    -0.10
     Stap
    -0.09
    æģ¶
    -0.09
    ä½łåĸľæ¬¢
    -0.09
    ugi
    -0.09
    -www
    -0.09
    ä¼ĺå¼Ĥ
    -0.09
    æĻ¯å¾·
    -0.08
    OTH
    -0.08
    åļ£
    -0.08
    POSITIVE LOGITS
    rese
    0.09
    aras
    0.09
    ansk
    0.09
    å¢Ļä¸Ĭ
    0.08
    aten
    0.08
    ç¿¥
    0.08
    çĵ£
    0.08
    æ¯į
    0.08
    ãģ¹
    0.08
    :message
    0.08
    Activations Density 0.007%

    No Known Activations