© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    bookmark

    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
    bos
    -0.10
    ÑĩаÑĤ
    -0.10
    å¤ĸåĽ½äºº
    -0.10
    roker
    -0.09
    utive
    -0.09
    baugh
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    ughter
    -0.08
     Merchant
    -0.08
    rics
    -0.08
    POSITIVE LOGITS
    æģĤ
    0.12
    æľ¬ç«Ļ
    0.09
    æ¦Ķ
    0.09
    ÙĦÙĬ
    0.09
    ÙĬÙĩ
    0.09
    æīī
    0.09
    OrUpdate
    0.09
    åĨĬ
    0.08
    åĪĩãĤĮ
    0.08
    çľ¼éķľ
    0.08
    Activations Density 0.005%

    No Known Activations