© 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. 20516
    Prev
    Next
    INDEX
    Explanations

    social acceptance and approval

    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
    åŀĴ
    -0.12
    æĶ¾è¿ĩ
    -0.10
    ç¥Ī祷
    -0.10
    ç£Ĭ
    -0.09
    èĭ¦èĭ¦
    -0.09
    æŃ»èĢħ
    -0.09
    绣çŃ¹
    -0.09
    æħij
    -0.09
    лем
    -0.09
    æ¯ĶæĪij
    -0.09
    POSITIVE LOGITS
    alo
    0.10
    å¼ģ
    0.09
    è¦ģåľ¨
    0.09
    èİ«
    0.09
     careers
    0.09
    ä¸ĢæŶ
    0.09
    æĻĴ
    0.08
    çļĦåľ°ä½į
    0.08
    avic
    0.08
     Career
    0.08
    Activations Density 0.201%

    No Known Activations