© 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. 8271
    Prev
    Next
    INDEX
    Explanations

    family and gendered individuals

    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
    å¥
    -0.12
    éĹ³
    -0.11
    éķŃ
    -0.10
    ìĬ¬
    -0.10
    è°ģçŁ¥
    -0.10
    oller
    -0.10
    åħ¨éķĩ
    -0.10
    .pivot
    -0.10
    ä»ĸçŁ¥éģĵ
    -0.10
    大å¸Ī
    -0.09
    POSITIVE LOGITS
     alike
    0.12
    æīĺ
    0.08
    以åıĬ
    0.08
    radi
    0.08
    p
    0.08
    以åıĬåħ¶ä»ĸ
    0.07
    s
    0.07
    arak
    0.07
    åIJĦæľī
    0.07
    posix
    0.07
    Activations Density 0.152%

    No Known Activations