© 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. 5729
    Prev
    Next
    INDEX
    Explanations

    past tense action verbs

    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
    å©Ĩ
    -0.10
    çªĿ
    -0.09
    èĬ¾
    -0.09
    .getHours
    -0.08
    ç»
    -0.08
     bè
    -0.08
    å°±è¶Ĭ
    -0.08
    bei
    -0.08
    被åĬ¨
    -0.08
    å·±
    -0.08
    POSITIVE LOGITS
    å¾Ĺå¾Ī
    0.11
    éħįæľī
    0.10
    ness
    0.09
    æľīè¶³å¤ŁçļĦ
    0.09
    å¾Ī好
    0.09
    è¦ģåģļ好
    0.09
    æĶ¯
    0.09
    æľīä¸įåIJĮçļĦ
    0.09
    樯
    0.09
    è®°å¾Ĺ
    0.09
    Activations Density 0.209%

    No Known Activations