© 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. 36851
    Prev
    Next
    INDEX
    Explanations

    way, far, much followed by comparative

    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
    otos
    -0.09
    æĵį
    -0.08
    ç¬ijç¬ij
    -0.08
    å¾ĺå¾Ĭ
    -0.08
    éĹªçĶµ
    -0.08
    kim
    -0.08
    æĥĭ
    -0.08
    åĩij
    -0.07
    entially
    -0.07
    igt
    -0.07
    POSITIVE LOGITS
     more
    0.10
    æĽ´åĬł
    0.10
    ãģ®æĸ¹ãģĮ
    0.10
     ×Ļ×ķתר
    0.09
    大çļĦ
    0.09
    æĽ´ä¸º
    0.09
    å¤ļåľ°
    0.09
    建åįİ
    0.09
    æ¯ĶæĪij
    0.09
     mote
    0.09
    Activations Density 0.064%

    No Known Activations