© 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. 5767
    Prev
    Next
    INDEX
    Explanations

    after initial diagnosis or training

    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
     Gim
    -0.08
    afen
    -0.08
     Vest
    -0.08
    éģ¿
    -0.08
    OWN
    -0.08
    vue
    -0.08
    ç½ijåıĭ们
    -0.08
     EMP
    -0.08
    ä¸ĢéĹ´
    -0.08
    诣
    -0.08
    POSITIVE LOGITS
    æŀ¶åŃIJ
    0.11
    æĦıè¯ĨåĪ°
    0.10
    UNET
    0.09
    ä¹ĭæĹ¥èµ·
    0.09
    либо
    0.09
    ç»Ļä»ĸ们
    0.09
    é¦ĸ次
    0.08
    åħī彩
    0.08
    解åĨ³éĹ®é¢ĺ
    0.08
    ansi
    0.08
    Activations Density 0.040%

    No Known Activations