© 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. 23635
    Prev
    Next
    INDEX
    Explanations

    describing subjects or sequences

    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
    anka
    -0.11
     crown
    -0.09
    åģļåĪ°
    -0.09
    对èĩªå·±çļĦ
    -0.09
    ç²¼
    -0.09
    对åѦçĶŁ
    -0.09
    è¿ĻéĩĮæĺ¯
    -0.09
    ᾶ
    -0.08
    éĽĦåİļ
    -0.08
    éľŀ
    -0.08
    POSITIVE LOGITS
    éķIJ
    0.09
    ä¸Ģ家
    0.09
    ormal
    0.09
    åľ¨ä¸Ģ个
    0.09
    orm
    0.09
    EIF
    0.09
    ä¸Ģäºĭ
    0.09
     diplom
    0.09
    emic
    0.08
    åħ±åIJĮåıijå±ķ
    0.08
    Activations Density 0.078%

    No Known Activations