© 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. 26328
    Prev
    Next
    INDEX
    Explanations

    movie and television actors

    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
    ibia
    -0.10
    ä¸į对
    -0.09
    纺
    -0.09
    ä¼½
    -0.09
    润
    -0.09
    æĬķæľº
    -0.08
     Washer
    -0.08
    å¤ĸçķĮ
    -0.08
    isque
    -0.08
    irk
    -0.08
    POSITIVE LOGITS
    èĮ¬
    0.09
    æĤį
    0.09
    BLE
    0.08
    åĬ¨ä½ľ
    0.08
    osto
    0.08
    èĮ§
    0.08
    ellas
    0.08
    èµ·æĿ¥äºĨ
    0.08
    éĻ·
    0.08
    tape
    0.08
    Activations Density 0.013%

    No Known Activations