© 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. 47620
    Prev
    Next
    INDEX
    Explanations

    sex and intercourse

    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
    该å¦Ĥä½ķ
    -0.10
    æ®´
    -0.09
    æ°¸åĪ©
    -0.09
    æ´Ĵ
    -0.09
    ilver
    -0.09
    izr
    -0.09
    ä¸ĢåĪĨ
    -0.09
    éĢł
    -0.08
    ness
    -0.08
    ervo
    -0.08
    POSITIVE LOGITS
    çĽ²
    0.12
    able
    0.10
    emin
    0.10
    enci
    0.09
    blind
    0.09
    æݾ
    0.09
    abled
    0.09
    exion
    0.09
    èĬ¥
    0.08
    ë§Ŀ
    0.08
    Activations Density 0.010%

    No Known Activations