© 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. 23961
    Prev
    Next
    INDEX
    Explanations

    male and female counts

    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
    Catch
    -0.10
    è¿Ľé£Ł
    -0.09
    æĥ´
    -0.09
    dek
    -0.09
    ç³ĸæŀľ
    -0.09
    æ¿¡
    -0.09
    ç½į
    -0.09
    çĵł
    -0.09
    å¯Į
    -0.09
    èħ±
    -0.08
    POSITIVE LOGITS
    çĶ·æĢ§
    0.29
    女æĢ§
    0.27
    çĶ·å¥³
    0.26
     male
    0.25
    æĢ§åĪ«
    0.25
     female
    0.24
    çĶ·
    0.24
     gender
    0.24
    female
    0.22
    male
    0.21
    Activations Density 0.274%

    No Known Activations