© 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. 61464
    Prev
    Next
    INDEX
    Explanations

    located at or in

    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
    æļĩ
    -0.09
    pth
    -0.09
    è¿Ļ个èģĮä¸ļ
    -0.09
    äºŃ
    -0.08
     tid
    -0.08
    (Optional
    -0.08
    éļ¾åħ³
    -0.08
    æĪĺ
    -0.08
    å¿ĹæĦ¿
    -0.08
    çķĻä½ı
    -0.08
    POSITIVE LOGITS
    ä½įäºİ
    0.10
    .getBounds
    0.10
    åħ¬åħ±äº¤éĢļ
    0.09
    交éĢļ
    0.09
    欢è¿İ大家
    0.09
    Directions
    0.09
     coordinates
    0.09
    coordinates
    0.09
    çļĦæĸ¹åIJij
    0.09
     Directions
    0.09
    Activations Density 0.054%

    No Known Activations