© 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. 31809
    Prev
    Next
    INDEX
    Explanations

    greatest successful best teams

    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
    åħĥå®Ŀ
    -0.09
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    igers
    -0.08
    缸å½ĵ
    -0.08
    eda
    -0.08
    aton
    -0.08
    æĭĹ
    -0.08
    è¿ĺ好
    -0.07
    è¿Ļä¹Ī大
    -0.07
    ä¸į足以
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.17
    å¾Ģå¾Ģ
    0.15
    éĤ£äºĽ
    0.14
    æīįæĺ¯çľŁæŃ£
    0.14
    æīįæĺ¯
    0.11
    è¶Ĭæĺ¯
    0.11
    æľĢ容æĺĵ
    0.11
    ä¸įä¸Ģå®ļ
    0.11
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.11
    æĺĻ
    0.10
    Activations Density 0.071%

    No Known Activations