© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38115
    Prev
    Next
    INDEX
    Explanations

    parentheses around specific words

    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
    /or
    -0.10
    essler
    -0.09
    æĦıå¿Ĺ
    -0.09
    oppers
    -0.08
     Stark
    -0.08
    tres
    -0.08
    审
    -0.08
    缴èĩ³
    -0.08
    èĮ¬
    -0.08
    енно
    -0.08
    POSITIVE LOGITS
    ãĢģ“
    0.22
    ãĢģãĢĮ
    0.12
    åŃĹæł·
    0.12
    è¿Ļåıª
    0.10
    ä¼ĹçŃ¹
    0.09
    为主é¢ĺçļĦ
    0.09
    éĤ£åıª
    0.09
    åĩ¿
    0.09
    uff
    0.08
    ç»į
    0.08
    Activations Density 0.593%

    No Known Activations