© 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. 20925
    Prev
    Next
    INDEX
    Explanations

    victim or victims

    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
    èĻļ空
    -0.10
    å£ħ
    -0.09
     WITHOUT
    -0.09
    æĭ®
    -0.09
    å¿ħä¸įåı¯
    -0.09
    INES
    -0.08
    è¿¥
    -0.08
    çŀ¥
    -0.08
    åħľ
    -0.08
    ä½łåĸľæ¬¢
    -0.08
    POSITIVE LOGITS
    åıĹ害
    0.21
    åıĹ害èĢħ
    0.21
     victims
    0.19
    åıĹ害人
    0.19
     victim
    0.18
    被害
    0.18
    victim
    0.17
     vÃŃctima
    0.16
     Victims
    0.16
    被害人
    0.15
    Activations Density 0.064%

    No Known Activations