© 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. 63044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĬĽæ±Ĥ
    -0.11
    å°ıæŶåīį
    -0.10
    好åIJĹ
    -0.10
    æŃ£æĸĩ
    -0.10
    ivec
    -0.10
    ÙĪرÙĪ
    -0.09
     год
    -0.09
    ä¸Ģ件
    -0.09
    åĽ¾æ¡Ī
    -0.09
    éŃĶæľ¯
    -0.09
    POSITIVE LOGITS
     att
    0.09
    åĬ©
    0.09
    åŃ
    0.09
    wel
    0.08
    lest
    0.08
    ä¸İåħ¶
    0.08
    å¦Ĥä¸ĭ
    0.07
    åģľçĶµ
    0.07
    éħ¬
    0.07
    att
    0.07
    Activations Density 0.000%

    No Known Activations