© 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. 567
    Prev
    Next
    INDEX
    Explanations

    selfie, convention, player, game, anime

    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
    é«ĺçŃīéĻ¢æł¡
    -0.10
    糸
    -0.09
    æİĮæı¡äºĨ
    -0.09
    åIJįæ°Ķ
    -0.09
    æķĿ
    -0.09
    åīįéĢĶ
    -0.08
    éĹ·
    -0.08
    R
    -0.08
    éĨª
    -0.08
    ä¹Łå¸ĮæľĽ
    -0.08
    POSITIVE LOGITS
     Knox
    0.10
    ç¬Ļ
    0.10
    楯
    0.09
    æī®æ¼Ķ
    0.09
    çĦ°
    0.09
     поÑĩ
    0.08
    orners
    0.08
     Ñģимв
    0.08
    essions
    0.08
    èĢħ
    0.08
    Activations Density 0.008%

    No Known Activations