© 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. 30771
    Prev
    Next
    INDEX
    Explanations

    license or velocity transport

    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
    åĨ¶
    -0.09
     Wag
    -0.09
    lobal
    -0.09
    OOM
    -0.09
    éħ¢
    -0.08
    bling
    -0.08
    ä¸Ģä½ĵåĮĸ
    -0.08
    累累
    -0.08
    .sess
    -0.08
    ноп
    -0.08
    POSITIVE LOGITS
    Ëĥ
    0.11
    æĢ»è£ģ
    0.09
    æĹ¥æĬ¥è®°èĢħ
    0.09
    æĢİèĥ½
    0.09
    éªij士
    0.08
    åµĺ
    0.08
    æĬ
    0.08
    æľīä»·åĢ¼
    0.08
    tti
    0.08
    èĮ¹
    0.08
    Activations Density 0.455%

    No Known Activations