© 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. 3570
    Prev
    Next
    INDEX
    Explanations

    arguments and specific challenges

    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
    æ½®
    -0.10
    çİ
    -0.09
    èķĻ
    -0.08
    个å¤ļ
    -0.08
    æĻģ
    -0.08
    ç²¾ç¥ŀçĹħ
    -0.08
    åŃĽ
    -0.08
    oug
    -0.08
    æ¯ĵ
    -0.08
    èĮģ
    -0.08
    POSITIVE LOGITS
    çIJIJ
    0.11
    æĹłåħ³
    0.10
    èĬĿ麻
    0.10
    çij
    0.10
    ç»Ĩå¾®
    0.09
     matters
    0.09
    æľ«ç«¯
    0.09
    ç»ħ
    0.08
    宵
    0.08
    次è¦ģ
    0.08
    Activations Density 0.059%

    No Known Activations