© 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. 36903
    Prev
    Next
    INDEX
    Explanations

    hate speech and illegal activities

    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
    贯彻
    -0.11
    åħĭæĭī
    -0.10
    ä¸įä¸ĭ
    -0.10
    edio
    -0.09
    è¯Ĩ
    -0.09
    åıŁ
    -0.09
    §è¡Į
    -0.08
    åIJĦæĸ¹
    -0.08
    รา
    -0.08
     паÑĢÑĤнеÑĢ
    -0.08
    POSITIVE LOGITS
     unofficial
    0.10
    esy
    0.09
    åĨĴ
    0.09
     Official
    0.09
    .openg
    0.09
    å®ŀè´¨æĢ§
    0.09
    ä»ħä¾ĽåıĤèĢĥ
    0.09
     hơi
    0.09
    umping
    0.09
    ä¸įåºĶ该
    0.09
    Activations Density 0.212%

    No Known Activations