© 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. 63749
    Prev
    Next
    INDEX
    Explanations

    suffix of animal 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
    åģļ人
    -0.09
    éĻĦåĬł
    -0.09
    å¢ĥ
    -0.09
    lias
    -0.08
    åľ¨å®¶
    -0.08
    åİĨ
    -0.08
    çĽijçĿ£ç®¡çIJĨ
    -0.08
    èĽĨ
    -0.08
    pez
    -0.08
    æ½¢
    -0.08
    POSITIVE LOGITS
    çĪ·
    0.11
    åĬ¨äºº
    0.09
    isman
    0.09
    isky
    0.09
    åIJĦçľģ
    0.09
    寮
    0.09
    ä¸ī级
    0.09
    itest
    0.09
     scho
    0.08
    ä¸įçķĻ
    0.08
    Activations Density 0.074%

    No Known Activations