© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34195
    Prev
    Next
    INDEX
    Explanations

    for verbs indicating purpose or necessity

    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
     unc
    -0.08
     commun
    -0.08
    çľĭä»ĸ
    -0.08
    è®
    -0.08
    ÆIJ
    -0.08
    çĤ¹åĦ¿
    -0.08
    æĴij
    -0.08
    æĻ
    -0.08
    èĬ±äºĨ
    -0.08
    祯
    -0.07
    POSITIVE LOGITS
    贵宾
    0.10
    nice
    0.10
    好è¿IJ
    0.09
    å¾Ĵ
    0.09
    elight
    0.09
    æ¿ĢåĬ¨
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    æ¢Ĩ
    0.09
    客家
    0.09
    elo
    0.09
    Activations Density 0.044%

    No Known Activations