© 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. 63809
    Prev
    Next
    INDEX
    Explanations

    nightclubs, clubs, nightlife

    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
    éĤĪ
    -0.11
    å°ıç¼ĸ
    -0.09
    åIJĦ个çݯèĬĤ
    -0.09
    éĤ¸
    -0.09
     hút
    -0.08
    caffe
    -0.08
     Sadd
    -0.08
    èĢĻ
    -0.08
     Subscribe
    -0.08
    ç«Łæĺ¯
    -0.08
    POSITIVE LOGITS
    èĭ¡
    0.10
    ipay
    0.10
    (patient
    0.09
    /bus
    0.09
     FIT
    0.09
    åĬłå¿«åıijå±ķ
    0.09
    .validator
    0.09
     Fit
    0.09
    èĭ¦
    0.08
    ãĥIJãĤ¹
    0.08
    Activations Density 0.025%

    No Known Activations