© 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. 19542
    Prev
    Next
    INDEX
    Explanations

    accumulating things or amounts

    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
    æľīæīĢ
    -0.10
    pictures
    -0.09
    æºIJæ³ī
    -0.09
     scaleY
    -0.09
    åĿ¤
    -0.09
    LEASE
    -0.09
    ç«ł
    -0.09
    åĮĹ大
    -0.09
    .HasKey
    -0.09
    纪
    -0.09
    POSITIVE LOGITS
    4
    0.09
    èµ·æĿ¥
    0.09
    atz
    0.09
    eler
    0.09
    ç©į
    0.09
    æĥĬ
    0.08
    æĸ°çļĦ
    0.08
    积
    0.08
    积累äºĨ
    0.08
    è¢ĸ
    0.08
    Activations Density 0.161%

    No Known Activations