© 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. 37431
    Prev
    Next
    INDEX
    Explanations

    important

    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
    åįĥå¹´
    -0.10
    maj
    -0.09
    è´¨éĩıéĹ®é¢ĺ
    -0.08
    UCH
    -0.08
     Trot
    -0.08
    éĩijèŀįæľįåĬ¡
    -0.08
    untlet
    -0.08
    åıĺå¾ĹæĽ´åĬł
    -0.08
    å¾ģæľį
    -0.08
    æľĭ
    -0.08
    POSITIVE LOGITS
    æĿ¥è®²
    0.11
    èĢĮè¨Ģ
    0.10
    许å¤ļ人
    0.09
    ija
    0.09
    çİ°éĺ¶æ®µ
    0.09
    ä¸ĸ人
    0.09
    è¿ĻæĶ¯
    0.09
    çłij
    0.09
    ä¸į论æĺ¯
    0.09
    è¿Ļ项
    0.08
    Activations Density 0.052%

    No Known Activations