© 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. 3064
    Prev
    Next
    INDEX
    Explanations

    brokeback Mountain, Guillermo del Toro

    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
    enson
    -0.10
    astes
    -0.09
    åľ¨æĪijçļĦ
    -0.08
     sos
    -0.08
    isko
    -0.08
     éĶ
    -0.08
    .Manifest
    -0.08
    滩
    -0.08
     Macros
    -0.08
    çĦĬæİ¥
    -0.08
    POSITIVE LOGITS
    premium
    0.09
    è§ģéĿ¢
    0.09
    zyst
    0.09
    å¼ĢåĬŀ
    0.08
    ëŀį
    0.08
    turned
    0.08
    åĨįè§ģ
    0.08
    MSN
    0.08
    æĹĮ
    0.08
    çļĦæĥħ
    0.08
    Activations Density 0.018%

    No Known Activations