© 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. 58341
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

    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
    ä»Ģä¹Īåij¢
    -0.12
    åı¯ä»¥è¯´æĺ¯
    -0.12
    æĪijè§īå¾Ĺ
    -0.12
    æĪij认为
    -0.11
    å½ĵçĦ¶æĺ¯
    -0.11
    ç¬ĶèĢħ
    -0.11
    å½ĵçĦ¶
    -0.11
    æį®è¯´
    -0.11
    被认为
    -0.10
    æĪijèĩªå·±
    -0.10
    POSITIVE LOGITS
    æīįæĺ¯çľŁæŃ£
    0.10
    æĺ¯å¤ļä¹Ī
    0.10
     could
    0.10
    æīįæĺ¯
    0.10
    æŃ¤ä¸¾
    0.09
    æľĢ好ä¸įè¦ģ
    0.08
    æĺ¯ä»¥
    0.08
    ä¹ĥæĺ¯
    0.08
    iba
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    Activations Density 0.694%

    No Known Activations