© 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. 38948
    Prev
    Next
    INDEX
    Explanations

    pride in providing

    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
    é¦ĸè¦ģ
    -0.11
     nạn
    -0.10
    éĩįå¿ĥ
    -0.09
    éĢ¡
    -0.09
     centr
    -0.09
    大éĻĨ
    -0.08
    é²ľ
    -0.08
    缮çļĦæĺ¯
    -0.08
    åĽłåħ¶
    -0.08
    ä¹ĭæīĢ以
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    å¾Ģ
    0.10
    alo
    0.10
    åIJĦæł·
    0.09
    å·¥ä½ľçļĦ
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    åIJĦéĥ¨éŨ
    0.09
    绸
    0.09
    åģļä¸ĢäºĽ
    0.08
    åģļ个
    0.08
    Activations Density 0.018%

    No Known Activations