© 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. 54394
    Prev
    Next
    INDEX
    Explanations

    born on or 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
    èĬ½
    -0.09
    åŁł
    -0.08
    é¼İ
    -0.08
     Meadows
    -0.08
    åħ¨æł¡
    -0.08
    sto
    -0.08
    ä¸įäºĨ
    -0.08
    ias
    -0.08
    å¨ģåĬĽ
    -0.08
    òng
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.12
    ä¿¡æģ¯åħ¬å¼Ģ
    0.10
    误ä¼ļ
    0.09
    .toolbox
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    æģŃ
    0.09
    æīİæł¹
    0.09
    æľįåĬ¡äºİ
    0.09
     ÐĺгÑĢ
    0.08
    Activations Density 0.170%

    No Known Activations