© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11514
    Prev
    Next
    INDEX
    Explanations

    design patterns

    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
    Clone
    -0.08
    ç¼Ń
    -0.08
    å°±æĺ¯ä¸ºäºĨ
    -0.08
    Sync
    -0.08
     tern
    -0.08
    _REASON
    -0.07
     idi
    -0.07
    å°±æĺ¯è¦ģ
    -0.07
    èĮķ
    -0.07
    าย
    -0.07
    POSITIVE LOGITS
    æĽ´åĥıæĺ¯
    0.13
    æµĶ
    0.11
    ç»ıèIJ¥æ´»åĬ¨
    0.10
    åķĦ
    0.10
    æ²±
    0.10
    æŃ£å¸¸çļĦ
    0.10
    äºĽä»Ģä¹Ī
    0.09
    ä¸įæĪIJ
    0.09
    èıĺ
    0.09
    ancel
    0.09
    Activations Density 0.185%

    No Known Activations