© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    physical and emotional abuse

    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
    æĮ½
    -0.10
    asin
    -0.10
    å¤įä»ĩ
    -0.10
    YM
    -0.10
    æĢħ
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    ç©´
    -0.09
    æIJŃ
    -0.09
    åķĨæľº
    -0.09
    ocoder
    -0.09
    POSITIVE LOGITS
    æļ´åĬĽ
    0.12
    èĻIJå¾ħ
    0.11
    严åİī
    0.11
     abuse
    0.11
     Abuse
    0.10
    家åºŃ
    0.10
     corpor
    0.10
    严ç¦ģ
    0.10
    æĬļæij¸
    0.10
     abusive
    0.09
    Activations Density 0.077%

    No Known Activations