© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    historical and geographical regions

    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
    ä¸ŃåĽ½åı¤ä»£
    -0.09
    éĥĬ
    -0.08
    å´ĩ
    -0.08
    agan
    -0.08
    è±ģ
    -0.08
    æ¯ıä¸Ģ天
    -0.08
    Spider
    -0.08
     Roman
    -0.08
    esan
    -0.08
    hin
    -0.07
    POSITIVE LOGITS
    illum
    0.10
    æ´®
    0.10
    åıĤè°ĭ
    0.10
    æĬ¥åĪĬ
    0.10
    [keys
    0.10
    å®ŀéĻħæݧåĪ¶
    0.09
    çĽ¸æľº
    0.09
    个çĻ¾åĪĨ
    0.09
    åĴĸåķ¡
    0.09
    udu
    0.09
    Activations Density 0.111%

    No Known Activations