© 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. 6952
    Prev
    Next
    INDEX
    Explanations

    future trends and current rates

    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
     Rid
    -0.11
    转身
    -0.09
    åħį责声æĺİ
    -0.09
    åĩ¤åĩ°
    -0.09
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    æĭħ
    -0.08
     rid
    -0.08
    едеÑĢ
    -0.08
    åıĺåİĭ
    -0.08
     ÑģÑĢазÑĥ
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.11
    çļĦ話
    0.11
    çļĦè¯Ŀ
    0.11
    ä¸ĭåİ»
    0.10
    continue
    0.10
    atis
    0.10
    å°Ĩ继ç»Ń
    0.10
    åĬ¿å¤´
    0.10
    åĬĽåº¦
    0.09
    å½ĵåīį
    0.09
    Activations Density 0.170%

    No Known Activations