© 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. 23763
    Prev
    Next
    INDEX
    Explanations

    between months and years

    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
    èľĥ
    -0.09
    oplay
    -0.09
     CALLBACK
    -0.09
    åıĪæĺ¯
    -0.09
    unch
    -0.09
    TRA
    -0.09
     Fet
    -0.09
     Roose
    -0.09
    aping
    -0.09
     Crom
    -0.09
    POSITIVE LOGITS
    /from
    0.15
    éĤ£éĩĮ
    0.10
    ä»Ģä¹Īåij¢
    0.10
    çļĦæŶéĹ´éĩĮ
    0.09
    gether
    0.09
    ãĤ
    0.09
    éĤ£åĦ¿
    0.09
    æĪIJ为ä¸ĢåIJį
    0.09
    妨
    0.09
    åħ¶ä½Ļ
    0.09
    Activations Density 0.068%

    No Known Activations