© 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. 5606
    Prev
    Next
    INDEX
    Explanations

    sons and daughters

    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
     couples
    -0.09
    æľ¨æĿIJ
    -0.09
    osti
    -0.09
    ÄĻd
    -0.08
    sole
    -0.08
     unf
    -0.08
    udy
    -0.08
    æijĪ
    -0.08
    纽
    -0.08
    ä¸Ģè´¯
    -0.08
    POSITIVE LOGITS
    овиÑĩ
    0.09
    åĪĨåĪ«æĺ¯
    0.09
    IBLE
    0.09
    åĪĨåĪ«ä¸º
    0.08
    åIJĮåŁİ
    0.08
    ç»ĦåĽ¢
    0.08
    åİĨå¹´
    0.08
     gsi
    0.08
    æĪijæĬĬ
    0.08
    äºī
    0.08
    Activations Density 0.030%

    No Known Activations