© 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. 1317
    Prev
    Next
    INDEX
    Explanations

    first, second, third, ninth

    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
     fond
    -0.09
    çī¹åĪ«æĺ¯åľ¨
    -0.09
    Anywhere
    -0.08
    å°¤åħ¶æĺ¯åľ¨
    -0.08
    ryn
    -0.08
    رÙģ
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    对ä»ĸ
    -0.08
    çĥĺ
    -0.08
    æ±Ģ
    -0.08
    POSITIVE LOGITS
     punch
    0.10
    é«ĺåİĭ
    0.10
    齿
    0.09
    éļ¶
    0.09
    eson
    0.09
    /weather
    0.08
    lte
    0.08
    icates
    0.08
    åIJĮä¸Ģ
    0.08
    ä½İ端
    0.08
    Activations Density 0.016%

    No Known Activations