© 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. 51634
    Prev
    Next
    INDEX
    Explanations

    living in a cave

    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
    以æѤ
    -0.10
    æĭ¿ä¸ĭ
    -0.09
    侧éĿ¢
    -0.09
     влад
    -0.09
    ORY
    -0.09
    icket
    -0.09
    åīįæľŁ
    -0.09
    æł¹æį®ä¸įåIJĮ
    -0.08
    èµ°ä¸ĭåİ»
    -0.08
    ä¸ĩåįĥçĵ¦
    -0.08
    POSITIVE LOGITS
    éĺī
    0.09
     Cand
    0.09
    äºĭä¸ļåıijå±ķ
    0.08
    è¿Ļåĩłå¤©
    0.08
    åıĪ被
    0.08
    /cpp
    0.08
    ä¸Ģè§Ĵ
    0.08
    åıijçĶŁçļĦ
    0.08
    屯
    0.08
    æŧ
    0.08
    Activations Density 0.026%

    No Known Activations