© 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. 49029
    Prev
    Next
    INDEX
    Explanations

    at the same time

    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
    upal
    -0.09
    å«Į
    -0.09
    ilee
    -0.08
    å¦ĩ
    -0.08
     Vit
    -0.08
    oller
    -0.08
    angan
    -0.08
    åıªéľĢ
    -0.08
    uil
    -0.08
    ï
    -0.08
    POSITIVE LOGITS
    åIJĮæĻĤãģ«
    0.16
    åIJĮæŶ
    0.16
    åIJĮæĹ¶ä¹Ł
    0.15
    çļĦåIJĮæŶ
    0.15
    ä¸İæѤåIJĮæŶ
    0.13
    åı¦ä¸Ģæĸ¹éĿ¢
    0.13
    åIJĮæĻĤ
    0.13
     ëıĻìĭľìĹIJ
    0.12
    åIJĮæĹ¶ä¹Łæĺ¯
    0.11
    çĦ¶
    0.11
    Activations Density 0.023%

    No Known Activations