© 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. 36753
    Prev
    Next
    INDEX
    Explanations

    instead use

    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
    ä¸įåıªæĺ¯
    -0.12
    ä¸įéĻIJ
    -0.11
    æĪijä¸įæĺ¯
    -0.11
    ä¸įæŃ¢
    -0.11
    ä¸įå±ŀäºİ
    -0.11
    ä¸įä¸Ģå®ļ
    -0.10
    ä¸įèĥ½åĨį
    -0.10
    ä¸įåı¯èĥ½
    -0.10
    ä¸įä»ħä»ħ
    -0.10
     not
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.17
    缸åıį
    0.17
    å¹²èĦĨ
    0.13
     ìĺ¤íŀĪ볤
    0.12
    æģ°æģ°
    0.11
     пÑĢоÑģÑĤо
    0.11
    å®Ŀè´µ
    0.10
     localVar
    0.10
    樯
    0.10
    Instead
    0.10
    Activations Density 0.057%

    No Known Activations