© 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. 53612
    Prev
    Next
    INDEX
    Explanations

    village and villagers

    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¥Ķ
    -0.11
    æĶ»çķ¥
    -0.10
    èµı
    -0.09
    éĶ²
    -0.09
    çĻ¾ä¸ĩ
    -0.08
    èĪ°
    -0.08
    è°ª
    -0.08
    é«ĺåĵģè´¨
    -0.08
    æĪ®
    -0.08
    åİĨåı²æĸĩåĮĸ
    -0.08
    POSITIVE LOGITS
    æĿijéĩĮ
    0.11
     villagers
    0.11
    åħ¨æĿij
    0.11
     village
    0.11
    æ°´æ³¥
    0.10
    å¦ĩ女
    0.10
    æĿij
    0.10
    家éĩĮ
    0.10
    åľ¨å®¶éĩĮ
    0.10
    åŁİéĩĮ
    0.09
    Activations Density 0.143%

    No Known Activations