© 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. 55100
    Prev
    Next
    INDEX
    Explanations

    equal opportunity and treatment

    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
    ä¸įå¿į
    -0.09
    æ¬
    -0.09
    cord
    -0.09
     Dia
    -0.09
    æľ¬åĽ½
    -0.09
    ÑģоÑĢ
    -0.09
    温æĥħ
    -0.08
    [source
    -0.08
     Glo
    -0.08
    家å±ŀ
    -0.08
    POSITIVE LOGITS
     access
    0.10
    æ²ī
    0.10
    æľºä¼ļ
    0.10
    åīįæıIJ
    0.10
     opportunities
    0.10
    çļĦæľºä¼ļ
    0.09
    éĻħ
    0.09
    èįĨ
    0.09
    çļĦåīįæıIJä¸ĭ
    0.09
    åıijå±ķæľºéģĩ
    0.09
    Activations Density 0.025%

    No Known Activations