© 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. 28136
    Prev
    Next
    INDEX
    Explanations

    payment mechanisms and pricing

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    æ´ŀå¯Ł
    -0.09
    ä¹Ŀæ±Ł
    -0.08
    è£ĺ
    -0.08
     needle
    -0.08
    ستر
    -0.08
    赤
    -0.08
    ottom
    -0.08
     sophistic
    -0.08
    绵
    -0.08
    POSITIVE LOGITS
    åĽºå®ļ
    0.12
    æµ®åĬ¨
    0.12
    è¿Ļç§įæĸ¹å¼ı
    0.12
    åĽºå®ļçļĦ
    0.11
    fixed
    0.11
     fixed
    0.11
    _fixed
    0.11
    .Fixed
    0.10
    Fixed
    0.10
    模å¼ı
    0.10
    Activations Density 0.088%

    No Known Activations