© 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. 26184
    Prev
    Next
    INDEX
    Explanations

    TMZ reports

    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
    åħ«åŃĹ
    -0.09
    ublisher
    -0.08
    æ·¡
    -0.08
     crossword
    -0.08
    ÇĶ
    -0.08
    ÑħваÑĤ
    -0.08
    å¿Ļç¢Į
    -0.07
    æij§
    -0.07
    诱
    -0.07
    bris
    -0.07
    POSITIVE LOGITS
    åľ¨æĪijåĽ½
    0.11
    åł¡
    0.11
    ians
    0.10
    çĬĬ
    0.10
    rides
    0.09
    åĢĴ
    0.09
    çł
    0.09
    æŁ¿
    0.09
    åĥŃ
    0.09
    éĶı
    0.09
    Activations Density 0.004%

    No Known Activations