© 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. 1145
    Prev
    Next
    INDEX
    Explanations

    still

    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
    åıįèĢĮ
    -0.12
    ä¸įåĨį
    -0.12
    åıĪæĺ¯
    -0.11
    ä¹Łæĺ¯ä¸Ģ个
    -0.11
    åıĪä¸Ģ次
    -0.11
    åıĪ好
    -0.10
    åıįåĢĴ
    -0.10
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.10
    ä¹ŁæĽ¾
    -0.10
    ä¹Łæĺ¯ä¸Ģç§į
    -0.10
    POSITIVE LOGITS
    ä¿ĿæĮģçĿĢ
    0.15
    åģľçķĻåľ¨
    0.12
    大å®Ĺ
    0.11
    åŃĺåľ¨çĿĢ
    0.09
    çķĻåľ¨
    0.09
    ANGO
    0.09
    åī©ä¸ĭ
    0.09
     Basics
    0.09
    åºĵéĩĮ
    0.09
    ä¸įå¿ĺ
    0.09
    Activations Density 0.331%

    No Known Activations