© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37649
    Prev
    Next
    INDEX
    Explanations

    yeast related terms

    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
    严峻
    -0.11
    æłĩçļĦ
    -0.10
    主ä¹ī
    -0.09
    è°İ
    -0.09
    è¦ģåĿļæĮģ
    -0.09
    ade
    -0.08
    ä¸įå°½
    -0.08
     ведÑĮ
    -0.08
    itarian
    -0.08
    æİĪ
    -0.08
    POSITIVE LOGITS
    erman
    0.12
    ermen
    0.11
    oppel
    0.10
    สà¸Ķ
    0.09
    mailto
    0.09
    lessly
    0.09
    atcher
    0.09
    ering
    0.09
    à¹ģห
    0.09
     Bowl
    0.08
    Activations Density 0.014%

    No Known Activations