© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40362
    Prev
    Next
    INDEX
    Explanations

    no followed by a list of things

    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
    Negative Logits
    æľīéĴ±
    -0.09
    è¿Ļä¸ī个
    -0.09
    ä½ĵæ£Ģ
    -0.09
    both
    -0.08
    çļĦ梦æĥ³
    -0.08
    _HOOK
    -0.08
    ÃŃo
    -0.08
    either
    -0.08
    ä¹Łæĺ¯
    -0.08
    çļĦè§Ĵèī²
    -0.08
    POSITIVE LOGITS
    æĹłä¸į
    0.09
    åŃĺåľ¨éĹ®é¢ĺ
    0.09
    het
    0.08
    ä¸ĢåĪĩ
    0.08
    pons
    0.08
    åħ¬å¼Ģåıij
    0.08
    ä»Ģä¹Īåij¢
    0.08
     vul
    0.08
    è¿ľè¿ľ
    0.08
    çĦ¶
    0.08
    Activations Density 0.026%

    No Known Activations