© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30143
    Prev
    Next
    INDEX
    Explanations

    fairness and equity

    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
    ä¹±
    -0.09
    oden
    -0.09
    å±ķæ¼Ķ
    -0.08
    äºĤ
    -0.08
    Labels
    -0.08
    çĬ¯
    -0.08
    mixed
    -0.08
    ohl
    -0.08
    好æľĭåıĭ
    -0.08
    æĪĸå¤ļ
    -0.08
    POSITIVE LOGITS
    åħ¬æŃ£
    0.15
    åħ¬å¹³
    0.15
    ä¸įåħ¬å¹³
    0.10
    满æĦıçļĦ
    0.10
    大纲
    0.10
    对å¾ħ
    0.09
    ãģª
    0.09
    -minded
    0.09
    ness
    0.09
    åIJĪçIJĨçļĦ
    0.09
    Activations Density 0.012%

    No Known Activations