© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51874
    Prev
    Next
    INDEX
    Explanations

    expresses regret or disappointment

    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
    çļĦéĤ£ç§į
    -0.09
    çļĦéĤ£ä¸ª
    -0.09
    ucas
    -0.09
    æĬ¥ä»ĩ
    -0.08
    éľĵ
    -0.08
    æ®Ĩ
    -0.08
     ÑĥвеÑĢ
    -0.08
    å¹³å®ī
    -0.08
    _ADV
    -0.08
     нек
    -0.08
    POSITIVE LOGITS
    åı¯æĥľ
    0.18
    éģĹæĨ¾
    0.15
    æĥĭ
    0.15
    åı¹æģ¯
    0.14
    è¾ľè´Ł
    0.11
    æĨ¾
    0.11
    æī¼
    0.10
     pity
    0.10
    æŀī
    0.10
    ä¸į好æĦıæĢĿ
    0.09
    Activations Density 0.042%

    No Known Activations