© 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. 2574
    Prev
    Next
    INDEX
    Explanations

    past tense verbs for roles or actions

    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
    ä»ĬåĽŀãģ¯
    -0.13
    æѤåĪ»
    -0.12
    ãģĵãĤĮãģĭãĤī
    -0.12
    缮åīįå·²
    -0.12
    çİ°åľ¨
    -0.12
     ÑģейÑĩаÑģ
    -0.12
    è¿Ļ次
    -0.12
    æŶæŶ
    -0.12
    ä»ĬæĻļ
    -0.12
    ä»Ĭãģ¯
    -0.12
    POSITIVE LOGITS
    è¿İæĿ¥äºĨ
    0.12
    å°±å¼Ģå§ĭ
    0.11
    å¼Ģå§ĭäºĨ
    0.10
    å¼Ģå§ĭ
    0.09
     begin
    0.09
     began
    0.09
     begins
    0.09
    ä¸İæŶ
    0.09
     оÑĩеÑĢед
    0.09
    ä¸ĢåĪĻ
    0.09
    Activations Density 0.449%

    No Known Activations