© 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. 5557
    Prev
    Next
    INDEX
    Explanations

    supernova, burial, league

    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
    -0.09
    ç½ļ款
    -0.08
    å°¾
    -0.08
     tail
    -0.08
    ä¼łæİĪ
    -0.08
    eline
    -0.07
    æĺ¯ä»¥
    -0.07
    æľīå¤ļä¹Ī
    -0.07
    æĹ¥å¤ľ
    -0.07
     ...
    -0.07
    POSITIVE LOGITS
    ALAR
    0.10
    ä¿IJ
    0.10
     eyewitness
    0.10
    åħħ足çļĦ
    0.09
    bara
    0.09
    ä¿Ŀé²ľ
    0.09
    翻身
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    åĭ¤å¥ĭ
    0.09
    iral
    0.09
    Activations Density 0.036%

    No Known Activations