© 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. 17608
    Prev
    Next
    INDEX
    Explanations

    favorite or favourites

    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
    æľįåĬ¡ä½ĵç³»
    -0.10
    obble
    -0.10
    èĿĩ
    -0.10
    ä¸īç§įèģĮä¸ļ
    -0.10
    ç³»
    -0.10
    å®ļä½į
    -0.09
    æĺ¯ä¸Ģ座
    -0.09
    æĸ½å·¥åįķä½į
    -0.09
    writers
    -0.09
     вÑĭпÑĥÑģ
    -0.09
    POSITIVE LOGITS
     favorites
    0.13
     favourites
    0.11
     favorite
    0.10
     favourite
    0.10
    亮çĤ¹
    0.10
     classic
    0.10
     staples
    0.09
    Favorites
    0.09
    favorite
    0.09
    ç»ıåħ¸
    0.09
    Activations Density 0.101%

    No Known Activations