© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52342
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĺķ
    -0.10
    _va
    -0.09
    ControlEvents
    -0.09
    è¦ģåĿļæĮģ
    -0.09
    avan
    -0.09
    elman
    -0.09
    SSIP
    -0.09
    å½ĵå¹´
    -0.09
    çŀ³
    -0.09
    ä¸ĭ次
    -0.08
    POSITIVE LOGITS
    æĪijä¸Ģ缴
    0.10
    æĪijå°±
    0.10
    ä¸ĢçĽ´åľ¨
    0.09
    æĪijåľ¨
    0.09
    æľī趣
    0.09
    ials
    0.09
    宣å¸ĥ
    0.09
    æİ¥åĪ°
    0.08
     Zug
    0.08
    åıijçĶŁäºĨ
    0.08
    Activations Density 0.084%

    No Known Activations