© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27642
    Prev
    Next
    INDEX
    Explanations

    film crew professions

    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
    åŀ£
    -0.10
    椿
    -0.09
    çļĦçĶŁæ´»
    -0.09
    é¢ĺæĿIJ
    -0.09
    _Local
    -0.09
    unchecked
    -0.09
    atron
    -0.09
    æĺ¥
    -0.08
    欢
    -0.08
    ä¸įå®ľ
    -0.08
    POSITIVE LOGITS
    èĢIJçĶ¨
    0.10
    åĿļå®Ī
    0.09
    éľ¾
    0.09
    afa
    0.09
    å¤ĦåĪĨ
    0.09
     ÑĢей
    0.08
    å³Ń
    0.08
    ç»ĻäºĨæĪij
    0.08
    æį®æĬ¥éģĵ
    0.08
    åĿļ
    0.08
    Activations Density 0.053%

    No Known Activations