© 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. 22399
    Prev
    Next
    INDEX
    Explanations

    named entities in lists

    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
    ä¸įåĥı
    -0.10
    çIJ¦
    -0.10
    å°±æѤ
    -0.10
    è°Ł
    -0.09
    èĮ¬
    -0.09
    çĶŁæ´»ä¹łæĥ¯
    -0.09
    ç«Ļç«ĭ
    -0.09
    åĽ½éĻħè´¸æĺĵ
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    çĢij
    -0.09
    POSITIVE LOGITS
    åIJĮæł·æĺ¯
    0.11
    çŃīçŃī
    0.09
    æĭīå¼Ģ
    0.08
     likewise
    0.07
    ark
    0.07
    another
    0.07
    èĻ½çĦ¶æĺ¯
    0.07
    å²³
    0.07
     pragma
    0.07
    ici
    0.07
    Activations Density 0.054%

    No Known Activations