© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38218
    Prev
    Next
    INDEX
    Explanations

    availability and convenience

    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
    æŀķ头
    -0.10
    æľīä»·åĢ¼çļĦ
    -0.09
    éļ¶
    -0.09
    èµĦåĬ©
    -0.09
    /uploads
    -0.09
    åłł
    -0.09
    çĶ±ä¸ŃåĽ½
    -0.09
    沧
    -0.09
    lander
    -0.09
     ord
    -0.08
    POSITIVE LOGITS
    便åĪ©
    0.10
    æĸ¹ä¾¿
    0.10
    å¿Ļ
    0.10
    สะà¸Ķวà¸ģ
    0.09
    便æį·
    0.09
    便äºİ
    0.09
    è·Ĺ
    0.08
     busy
    0.08
    åĩºå·®
    0.08
    éĢĢ
    0.08
    Activations Density 0.088%

    No Known Activations