© 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. 36948
    Prev
    Next
    INDEX
    Explanations

    buy something or first visit

    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
     ведÑĮ
    -0.12
    ä¹ŁåĽłæѤ
    -0.09
     {}.
    -0.09
    åIJ¦
    -0.09
    åĩłä¹İæīĢæľī
    -0.09
    ä¼ļæľī
    -0.08
     khá
    -0.08
    ãĢĤ
    -0.08
    åĪ«
    -0.08
    åĩłä¹İ
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.21
    ï¼ĮåĪĻ
    0.20
    çļĦ話
    0.17
    æŁIJ个
    0.16
    è¿Ļæł·çļĦè¯Ŀ
    0.15
    éĤ£ä½ł
    0.14
    æŁIJä¸Ģ
    0.14
    ëĭ¤ë©´
    0.14
    íķľëĭ¤ë©´
    0.14
     thì
    0.14
    Activations Density 0.477%

    No Known Activations