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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57733
    Prev
    Next
    INDEX
    Explanations

    war and strategy games

    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
    æ°¡
    -0.09
    åĪ©çī©
    -0.09
     spel
    -0.08
    rei
    -0.08
    åĥ¦
    -0.08
    åĬ©éķ¿
    -0.08
     Whitney
    -0.08
    رÙĬÙĨ
    -0.08
    æ®ĵ
    -0.08
    èµ°
    -0.07
    POSITIVE LOGITS
    åħµåĬĽ
    0.11
    èİ·èĥľ
    0.10
    çļĦæĪĺçķ¥
    0.10
    è·Ľ
    0.10
    æĪĺäºī
    0.10
    ä¼IJ
    0.10
    顾éĹ®
    0.09
    ideo
    0.09
    çļĦå®ŀåĬĽ
    0.09
    æĪĺçķ¥
    0.09
    Activations Density 0.110%

    No Known Activations