© 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. 9682
    Prev
    Next
    INDEX
    Explanations

    use pastry blender, working in, pass a small needle

    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
     Headquarters
    -0.09
    çĩİ
    -0.09
    æŀ¢
    -0.09
    åľ¨æĪijçľĭæĿ¥
    -0.09
    èĪ±
    -0.08
    æĢ»éĥ¨
    -0.08
    çħ¦
    -0.08
    绣
    -0.08
    åĹĦ
    -0.08
    æ´ĹèĦ¸
    -0.08
    POSITIVE LOGITS
    ries
    0.09
    ìĤ¼
    0.09
    å§Ķåijĺä¼ļ
    0.09
    å·¥ä½ľç»Ħ
    0.09
    å§Ķä¼ļ
    0.08
     undef
    0.08
    éĢĹ
    0.08
    ä¸ĭè¡Į
    0.08
    æľīåºı
    0.08
    unter
    0.08
    Activations Density 0.013%

    No Known Activations