© 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. 26834
    Prev
    Next
    INDEX
    Explanations

    also makes

    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
    åį³ä½¿
    -0.08
    åį³ä¾¿
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
    بÙĥ
    -0.08
    æ¶ķ
    -0.08
    åĭī强
    -0.08
    pri
    -0.08
    CMP
    -0.08
    æīįç®Ĺ
    -0.08
    åij¼å£°
    -0.07
    POSITIVE LOGITS
    带æĿ¥äºĨ
    0.18
    带æĿ¥
    0.15
    çļĦåIJĮæŶ
    0.14
    帶ä¾Ĩ
    0.13
     downside
    0.13
    代价
    0.13
    åIJĮæĹ¶ä¹Ł
    0.12
    ä½Ĩä¹Ł
    0.12
    带æĿ¥çļĦ
    0.12
    ä¹Łåı¯èĥ½
    0.12
    Activations Density 0.133%

    No Known Activations