© 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. 48009
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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¸ļ
    -0.08
     cola
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    opsis
    -0.08
     Near
    -0.08
    .ordinal
    -0.08
     Ferguson
    -0.07
    åĪ©
    -0.07
    æĦıæĥ³ä¸įåĪ°
    -0.07
     hang
    -0.07
    POSITIVE LOGITS
    æŃ£åľ¨
    0.18
    æŃ£åľ¨è¿Ľè¡Į
    0.12
     Äijang
    0.12
    ä¸ľè¥¿
    0.11
    缮åīįæŃ£åľ¨
    0.11
    ä½łè¦ģ
    0.10
    æĿ±è¥¿
    0.10
     estamos
    0.09
    æĿ¥è¢Ń
    0.09
    æĿ¥å®¾
    0.09
    Activations Density 0.087%

    No Known Activations