© 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. 19904
    Prev
    Next
    INDEX
    Explanations

    -ing or -ation followed by a noun

    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
    大è§Ħ模
    -0.10
    ä¸ºçĽ®æłĩ
    -0.10
    åĪ¶åĵģ
    -0.10
    æĭ¿åĪ°
    -0.09
    è¯Ħå§Ķ
    -0.09
    çĶŁäº§æĢ»åĢ¼
    -0.09
    ä¸ĢçĤ¹
    -0.09
    éĩįè¦ģçļĦ
    -0.09
    ness
    -0.09
    åıijå±ķä¸Ń
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.12
    æĸ¹å¼ı
    0.12
    èĮĥåĽ´
    0.11
    æľºåĪ¶
    0.11
    æľºä¼ļ
    0.11
    åĴĮæľįåĬ¡
    0.11
    éĿ¢ç§¯çº¦
    0.10
    æĹ¶æľº
    0.10
    å¥ijæľº
    0.10
    æĻĤãģ®
    0.10
    Activations Density 0.582%

    No Known Activations