© 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. 48994
    Prev
    Next
    INDEX
    Explanations

    people being / people that / people who

    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
    ä½ľèĢħæľ¬äºº
    -0.11
    转æĬĺ
    -0.10
    带ä¸Ĭ
    -0.10
    æľīä¸Ģä½į
    -0.09
    人群ä¸Ń
    -0.09
    大è¡Ĺ
    -0.09
    æľīä¸Ģç§į
    -0.09
    æľ¬äºº
    -0.09
    uta
    -0.09
    BOSE
    -0.08
    POSITIVE LOGITS
    æijĺ
    0.10
    ä¹ĭåīį
    0.09
    ndl
    0.08
    миÑĢ
    0.08
    claimer
    0.08
    ulet
    0.08
    destruct
    0.08
     else
    0.08
    媵
    0.08
     пен
    0.08
    Activations Density 0.026%

    No Known Activations