© 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. 37303
    Prev
    Next
    INDEX
    Explanations

    way to introduce examples

    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
    inters
    -0.09
    .identity
    -0.08
    åĪ©äºļ
    -0.08
    asar
    -0.08
    draft
    -0.08
    æİĮ
    -0.08
    ä¸įæĩĪ
    -0.08
    æķĻä½ł
    -0.08
    lobals
    -0.08
    åĨį说
    -0.07
    POSITIVE LOGITS
    ç»ĵå°¾
    0.10
    éģİãģĶ
    0.10
    ä»£æĽ¿
    0.10
    ç»ĵæĿŁ
    0.10
    åij¼åºĶ
    0.09
    å¢ŀæ·»
    0.09
    ç»ĵæĿŁäºĨ
    0.09
    è±¹
    0.09
    ucc
    0.09
    æĬķèµĦé¢Ŀ
    0.09
    Activations Density 0.057%

    No Known Activations