© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    childhood innocence optimism

    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
    èĤ¤
    -0.10
    åħ¨å®¶
    -0.10
    èĩªæķij
    -0.09
    缸å¤Ħ
    -0.08
     Athletics
    -0.08
    示èĮĥ
    -0.08
    çĨ
    -0.08
     Tig
    -0.08
    æIJı
    -0.08
     biography
    -0.08
    POSITIVE LOGITS
    浪漫
    0.14
    å¤©çľŁ
    0.13
    ç«¥è¯Ŀ
    0.12
    åŃ©ç«¥
    0.11
    å°ıæŶåĢĻ
    0.11
    æĨ§æĨ¬
    0.11
    æĥ³è±¡åĬĽ
    0.11
    梦æĥ³
    0.10
     Innoc
    0.10
    åIJijå¾Ģ
    0.10
    Activations Density 0.061%

    No Known Activations