© 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. 55890
    Prev
    Next
    INDEX
    Explanations

    expresses approval or liking

    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
    æĽ´éĢĤåIJĪ
    -0.10
    ä¸įéĢĤåIJĪ
    -0.10
    åį°è±¡
    -0.10
    ä¸į幸
    -0.09
    é¢ĩ为
    -0.09
    ãģªãĤĬ
    -0.08
    lik
    -0.08
    ä¸įéĢĤ
    -0.08
    å¦Ĥä½ķçľĭå¾ħ
    -0.08
    çļĦåį°è±¡
    -0.08
    POSITIVE LOGITS
    ç¼
    0.09
    ÑİÑī
    0.09
    itos
    0.09
    æŁ©
    0.09
    å¾Ģä¸ĭ
    0.09
    uma
    0.08
    ç®Ģ约
    0.08
    çķİ
    0.08
    ä»ĸæĺ¯ä¸Ģ个
    0.08
    æĿª
    0.08
    Activations Density 0.025%

    No Known Activations