© 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. 51904
    Prev
    Next
    INDEX
    Explanations

    anesthetic and nerve related terms

    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
    æ´ģåĩĢ
    -0.09
     prefect
    -0.09
    å¡Į
    -0.09
    æº
    -0.09
    æ¸ļ
    -0.09
    æIJŃ
    -0.08
    æ¡£
    -0.08
    å¢
    -0.08
    å¯ĨåĪĩ
    -0.08
    åĭ¤
    -0.08
    POSITIVE LOGITS
    éº»æľ¨
    0.12
    ajo
    0.10
    è§ī
    0.10
    åijĬ
    0.10
     nerves
    0.10
    æĦŁè§ī
    0.09
    ä¸ĢæŶ
    0.09
    åľ¨å¤ĸéĿ¢
    0.09
    红åĮħ
    0.09
    æ¸IJæ¸IJ
    0.09
    Activations Density 0.274%

    No Known Activations