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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52062
    Prev
    Next
    INDEX
    Explanations

    percentage off or dollar amounts off

    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
    å¨ĥå¨ĥ
    -0.11
    åĸĿèĮ¶
    -0.11
    åľ¨åŃ¦æł¡
    -0.10
    åľ¨æł¡
    -0.10
    orro
    -0.10
    erus
    -0.10
    读åIJİ
    -0.10
    LOAT
    -0.10
    ä¸įéĶĻçļĦ
    -0.10
    åŃļ
    -0.10
    POSITIVE LOGITS
     Umb
    0.09
     umb
    0.09
    ness
    0.08
    eness
    0.08
    archy
    0.08
    åį³å°ĨåĪ°æĿ¥
    0.07
    è¿ĩçļĦ
    0.07
    åĩºçİ°åľ¨
    0.07
     sale
    0.07
    (TIM
    0.07
    Activations Density 0.005%

    No Known Activations