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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9624
    Prev
    Next
    INDEX
    Explanations

    to name a few

    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
    	TokenName
    -0.10
     Shooter
    -0.09
    rocessing
    -0.09
    .mesh
    -0.09
    æĸĩåĮĸåĪĽæĦı
    -0.09
    ellij
    -0.09
    没è§ģè¿ĩ
    -0.09
    ç¼ľ
    -0.09
    æ¡ĮåŃIJä¸Ĭ
    -0.09
    æĢ»éĺŁ
    -0.09
    POSITIVE LOGITS
    åĩłä¸ª
    0.12
    åĩłå®¶
    0.12
     few
    0.11
    åĩł
    0.09
    åĩłçĤ¹
    0.09
    ãģĦãģıãģ¤ãģĭ
    0.09
    åĩłä½į
    0.09
    åĩłåĪĨ
    0.09
    ä»ħä¾ĽåıĤèĢĥ
    0.08
    åĩłä¸ªäºº
    0.08
    Activations Density 0.003%

    No Known Activations