© 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. 840
    Prev
    Next
    INDEX
    Explanations

    estrogen or estrogen-like

    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
    åĴ³
    -0.10
    _nl
    -0.09
    çĹ
    -0.09
    bury
    -0.09
    acom
    -0.08
    åĴĮæľįåĬ¡
    -0.08
     mash
    -0.08
    æı¡æīĭ
    -0.08
     promo
    -0.08
    ä¸Ńç§ij
    -0.08
    POSITIVE LOGITS
    å°ijæķ°
    0.10
    èİ«æĸ¯
    0.09
    è¶ħæłĩ
    0.09
    离ä¸įå¼Ģ
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    驾
    0.08
    åĪĨéĶĢ
    0.08
    åĢĻéĢī人
    0.08
    pill
    0.08
    .strftime
    0.08
    Activations Density 0.147%

    No Known Activations