© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51853
    Prev
    Next
    INDEX
    Explanations

    statement or 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
    åłª
    -0.10
     наÑĢ
    -0.10
     CType
    -0.09
    ulin
    -0.08
    å¼Ħ
    -0.08
    onitor
    -0.08
    vide
    -0.08
    åĬłåĪĨ
    -0.08
    engl
    -0.07
     commons
    -0.07
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.23
    è¿Ļè¯Ŀ
    0.17
    æĦıæĢĿæĺ¯
    0.12
    两åı¥
    0.11
    statement
    0.11
    äºĨä¸Ģåı¥
    0.11
    ä»Ģä¹ĪæĦıæĢĿ
    0.11
     statement
    0.11
    çļĦæĦıæĢĿ
    0.11
    åĩºèĩª
    0.11
    Activations Density 0.123%

    No Known Activations