© 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. 21099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     компани
    -0.09
     Elder
    -0.09
    æ·Ģ
    -0.09
    交代
    -0.08
    èİ«
    -0.08
    åIJĮå¿ĥ
    -0.08
    åIJ¯èĴĻ
    -0.08
    _LS
    -0.08
    erno
    -0.08
    ìĽIJ
    -0.08
    POSITIVE LOGITS
    èĢ¿
    0.10
     unw
    0.10
    åĵ©
    0.09
    ä¸ĢçĤ¹
    0.09
    æŀī
    0.09
    使åij½
    0.09
    é¥Ńèıľ
    0.09
    ifa
    0.09
    èıľ
    0.09
    ä»ĵ
    0.08
    Activations Density 0.000%

    No Known Activations