© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38379
    Prev
    Next
    INDEX
    Explanations

    hear about or calls for

    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
    认è¯Ĩ
    -0.10
    注å®ļ
    -0.09
    arge
    -0.09
    å®ŀåľ°
    -0.09
    ackle
    -0.08
    æĶ¶åıĹ
    -0.08
     unw
    -0.08
    åŦ
    -0.08
    åħ¨æł¡
    -0.08
    ä¹Łä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    åIJĦå¼Ĥ
    0.11
    곤
    0.10
    åijĬè¯īä½ł
    0.10
    åºł
    0.10
    è¯Ł
    0.10
    çĸ²æĥ«
    0.09
    çļĦ身影
    0.09
    åĿĬ
    0.09
    å¿Ŀ
    0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.09
    Activations Density 0.241%

    No Known Activations