© 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. 51361
    Prev
    Next
    INDEX
    Explanations

    quality control and defects

    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
    å·©åĽº
    -0.09
    赫
    -0.09
    íĿ¥
    -0.08
     Antoine
    -0.08
    Pink
    -0.08
     Patterson
    -0.08
    ease
    -0.08
     fav
    -0.08
    èĥĮåıĽ
    -0.08
    åºŃéĻ¢
    -0.08
    POSITIVE LOGITS
    çijķçĸµ
    0.13
    åIJĪæł¼
    0.13
    çŃī级
    0.13
    ä¸įåIJĪæł¼
    0.12
    è¯Ħ级
    0.12
    产åĵģè´¨éĩı
    0.11
    æŃ£åĵģ
    0.11
    ç²¾åĵģ
    0.11
    è´¨éĩı
    0.10
     rejects
    0.10
    Activations Density 0.148%

    No Known Activations