© 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. 35400
    Prev
    Next
    INDEX
    Explanations

    weblog and blog posts

    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
    æ¦ľ
    -0.10
     hẳn
    -0.10
    weed
    -0.09
    èİĵ
    -0.09
     bè
    -0.08
    åĪ¶è®¢
    -0.08
    çļĦæľ¬è´¨
    -0.08
    æ°´åŁŁ
    -0.08
    ches
    -0.08
    _DIRECT
    -0.08
    POSITIVE LOGITS
    ä½ĥ
    0.10
    èĦĤ
    0.09
    eton
    0.09
    à¸Ĭà¸Ļ
    0.09
    çľ¼åħī
    0.08
    BAT
    0.08
    prefix
    0.08
    åIJ¬å¾Ĺ
    0.08
    armed
    0.08
    è¾ĩ
    0.08
    Activations Density 0.001%

    No Known Activations