© 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. 62297
    Prev
    Next
    INDEX
    Explanations

    academic, medical, and research institutions

    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
    باÙĥ
    -0.08
    inia
    -0.08
    ç¼ĩ
    -0.08
    鸿
    -0.08
    á»ĺ
    -0.08
    pest
    -0.07
     intermediate
    -0.07
    opsis
    -0.07
    åĪĨå±Ģ
    -0.07
    medium
    -0.07
    POSITIVE LOGITS
    çłĶ究ä¸Ńå¿ĥ
    0.15
    é¦ĸåĪĽ
    0.10
    çłĶåıijä¸Ńå¿ĥ
    0.10
    ä¸ĸçķĮä¸Ģæµģ
    0.10
    æķĻæİĪ
    0.10
    achu
    0.09
    çłĶ究人åijĺ
    0.09
    赧
    0.09
    çļĦçłĶ究
    0.09
    çłĶ究
    0.09
    Activations Density 0.067%

    No Known Activations