© 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. 35545
    Prev
    Next
    INDEX
    Explanations

    site links

    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
    æľ¬æĬ¥
    -0.09
    饿
    -0.09
    ç»ıèIJ¥èĮĥåĽ´
    -0.09
    åĪ°è´¦
    -0.09
    è§IJ
    -0.08
    å®ĺæĸ¹å¾®åįļ
    -0.08
    åİ®
    -0.08
    æľ¬æĬ¥è®¯
    -0.08
    èİĵ
    -0.08
    æĢ»åħ¬åı¸
    -0.08
    POSITIVE LOGITS
    SITE
    0.10
     Site
    0.10
     site
    0.10
    ãĥªãĥ³ãĤ¯
    0.09
    idget
    0.09
    Navigator
    0.09
    ç§ijæĻ®
    0.09
    ç½Ĺ
    0.08
    .Site
    0.08
    (site
    0.08
    Activations Density 0.257%

    No Known Activations