© 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. 51662
    Prev
    Next
    INDEX
    Explanations

    altruistic others

    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
    让ä»ĸ们
    -0.12
    è®ĵä»ĸåĢij
    -0.10
    ä»ĸä»¬åľ¨
    -0.10
    ä¸įçķĻ
    -0.10
    ç»Ļä»ĸ们
    -0.09
    cul
    -0.09
    ä»ĸ们çļĦ
    -0.09
    åıijæĮ¥äºĨ
    -0.09
     background
    -0.08
    åºĶæľīçļĦ
    -0.08
    POSITIVE LOGITS
    ç»ĻåĪ«äºº
    0.18
    åĪ«äººçļĦ
    0.18
    åĪ«äºº
    0.17
    ä»ĸ人
    0.17
     others
    0.15
    ä¸İåħ¶ä»ĸ
    0.12
    åĪ¥äºº
    0.12
    others
    0.12
    Others
    0.12
    éĤ»å±ħ
    0.12
    Activations Density 0.154%

    No Known Activations