© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21226
    Prev
    Next
    INDEX
    Explanations

    however was

    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
    ä½ľé£İ
    -0.10
    å¾Īå¥½åľ°
    -0.10
    è§īå¾Ĺå¾Ī
    -0.09
    aran
    -0.09
    ÑĨе
    -0.09
     Dollar
    -0.09
    æ´½
    -0.09
    å¾Īå·®
    -0.08
     Rams
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.12
    æīįæĺ¯
    0.11
    羣æŃ£
    0.11
    æīįæĺ¯çľŁæŃ£
    0.11
    æľĢéĩįè¦ģ
    0.10
    æľĢ为
    0.10
    èµŀåı¹
    0.10
    åį´æĺ¯
    0.10
    æľĢåħ³éĶ®çļĦ
    0.10
    åİī害
    0.10
    Activations Density 0.051%

    No Known Activations