© 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. 58461
    Prev
    Next
    INDEX
    Explanations

    own business or company

    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
     ted
    -0.09
    ted
    -0.08
    产ä¸ļåįĩ级
    -0.08
    æĸĻ
    -0.08
    -0.08
    ijo
    -0.08
    继
    -0.08
    olan
    -0.08
    uum
    -0.08
    为æĬĵ
    -0.08
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.12
    çį¨ç«ĭ
    0.11
    곡
    0.11
    ç²¾
    0.10
     independ
    0.10
    æĮŁ
    0.10
    _own
    0.10
    Own
    0.10
    èĩªå·±çļĦ
    0.10
    ä¸Ģ头
    0.10
    Activations Density 0.052%

    No Known Activations