© 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. 54026
    Prev
    Next
    INDEX
    Explanations

    ask for specific questions

    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
    æĪijå¿ĥéĩĮ
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    ç»ĻæĪij们
    -0.10
    çģ
    -0.10
    äºĨæĪijçļĦ
    -0.09
    对æĪij说
    -0.09
    æĪij们ä¼ļ
    -0.09
    éĢļçŁ¥ä¹¦
    -0.08
    anel
    -0.08
    æĪijéĻ¢
    -0.08
    POSITIVE LOGITS
    对æĸ¹
    0.11
    éĹ®éĹ®
    0.10
    çĿ£ä¿ĥ
    0.10
     ask
    0.10
    asking
    0.10
    éĹ®ä»ĸ
    0.09
    åijĬè¯ī
    0.09
    çĻ½éĽª
    0.09
    迫使
    0.09
     asking
    0.09
    Activations Density 0.058%

    No Known Activations