© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51135
    Prev
    Next
    INDEX
    Explanations

    first events or stages

    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
    รม
    -0.09
    ä¸Ģç±»
    -0.09
    åĪĨè£Ĥ
    -0.09
    ór
    -0.09
     rais
    -0.09
    LAG
    -0.09
    CLE
    -0.09
    ä¸įç»ı
    -0.09
     Ned
    -0.08
    磫
    -0.08
    POSITIVE LOGITS
    第ä¸Ģ次
    0.10
    åĮħåĮħ
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.09
    æݥ触åĪ°
    0.09
    æĩĤäºĭ
    0.09
    æĺ¯ä¸Ģ件
    0.09
    çļĦç¾İ好
    0.08
     Malk
    0.08
    çĤİ
    0.08
    ä¹ĭåŁİ
    0.08
    Activations Density 0.190%

    No Known Activations