© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8129
    Prev
    Next
    INDEX
    Explanations

    inherent problems

    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
    å¢ŀå̼
    -0.08
    æľīåĪ©
    -0.08
     Entrance
    -0.07
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    -0.07
    æıIJåĢ¡
    -0.07
    èIJ½æĪ·
    -0.07
    á»¶
    -0.07
    工夫
    -0.07
     ArrayBuffer
    -0.07
    å·¥ä½ľçļĦ
    -0.07
    POSITIVE LOGITS
    åıijçĶŁçļĦ
    0.12
    æİ¥è¿ŀ
    0.10
    å±ĢåĬ¿
    0.10
     diá»ħn
    0.10
    éľĩæĴ¼
    0.10
    åıijçĶŁåľ¨
    0.10
    åħ¨çIJĥ
    0.10
    æĸ°éĹ»
    0.10
    åºıå¹ķ
    0.10
    常æĢģ
    0.09
    Activations Density 0.171%

    No Known Activations