© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    serving portions

    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
    çļĦåij³éģĵ
    -0.09
    没æľīå¿ħè¦ģ
    -0.09
    راء
    -0.09
    ä¸į太好
    -0.09
    avin
    -0.09
    å±Ī
    -0.09
     Ag
    -0.08
    arding
    -0.08
    è¿ĩ滤
    -0.08
    åľ¨è·¯ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    å®ļéĩı
    0.10
    .dm
    0.10
    éĩıåĮĸ
    0.10
    ä¸Ģéģĵ
    0.10
    Sizes
    0.10
     repl
    0.10
    æĸ°çļĦä¸Ģ
    0.09
    å©Ģ
    0.09
    å¸Ĥåľºè§Ħ模
    0.09
    尺寸
    0.09
    Activations Density 0.057%

    No Known Activations