© 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. 49976
    Prev
    Next
    INDEX
    Explanations

    war or words after "in"

    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
    æĮ£æīİ
    -0.09
    åĪ°æľŁ
    -0.09
    大å¦Ī
    -0.09
    ä¸ĢæŶ
    -0.08
    adius
    -0.08
    æĶ¶èİ·
    -0.08
    å¿ı
    -0.08
    害ç¾ŀ
    -0.08
    IMS
    -0.08
    IFS
    -0.08
    POSITIVE LOGITS
    çļĦéĤ£ä¸Ģ
    0.10
    OFFSET
    0.10
    getApplication
    0.09
    æİĤ
    0.09
    åĪĿå§ĭ
    0.09
    å¼Ģåľº
    0.09
    æ³Ĭ
    0.09
    åĪĿ次
    0.09
    注åħ¥
    0.09
    çĽ¸ä¿¡å¤§å®¶
    0.09
    Activations Density 0.124%

    No Known Activations