© 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. 10916
    Prev
    Next
    INDEX
    Explanations

    cities and acronyms

    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
     territory
    -0.08
    åĩºè·¯
    -0.08
    æĬķåħ¥åĪ°
    -0.08
    ãģĿãģĨãģª
    -0.08
     vox
    -0.08
     Mash
    -0.08
    åİŁæľīçļĦ
    -0.08
    åĪ©äºļ
    -0.08
    ä¹ĥèĩ³
    -0.07
    éļ§éģĵ
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¹ķ
    0.11
    ä¼ļè®®ä¸Ĭ
    0.11
    åĨ³å®ļ
    0.11
    åĨ³è®®
    0.10
    決å®ļ
    0.10
     ê²°ìłķ
    0.09
    æݬ
    0.09
    ä¾Ī
    0.09
    诤
    0.09
    tra
    0.09
    Activations Density 0.041%

    No Known Activations