© 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. 7391
    Prev
    Next
    INDEX
    Explanations

    that is

    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
     globals
    -0.10
    /umd
    -0.10
    globals
    -0.09
    巴士
    -0.09
    主线
    -0.09
    _smart
    -0.09
     Kapoor
    -0.09
     Baths
    -0.08
    æķ£çĥŃ
    -0.08
    Globals
    -0.08
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.22
    ä¹Łå°±æĺ¯è¯´
    0.17
    ãģ¤ãģ¾ãĤĬ
    0.16
    ä»Ģä¹ĪæĦıæĢĿ
    0.13
    æĺ¯æĮĩ
    0.13
    åį³
    0.13
    æĮĩçļĦæĺ¯
    0.12
     tức
    0.11
    ä¿Ĺ称
    0.11
     cioè
    0.11
    Activations Density 0.264%

    No Known Activations