© 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. 48769
    Prev
    Next
    INDEX
    Explanations

    actions beginning

    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
    èĩ»
    -0.11
    Ø´Ùĩر
    -0.09
    æĸ¥
    -0.09
    æĦıè¦ĭ
    -0.08
    езн
    -0.08
    翦
    -0.08
    etable
    -0.08
     okreÅĽ
    -0.08
    _cast
    -0.08
    ç»Īäºİ
    -0.08
    POSITIVE LOGITS
    深深çļĦ
    0.12
    iate
    0.10
    æ¶Īè´¹åįĩ级
    0.10
    åĽĽå¤Ħ
    0.09
    äºĨä¸Ģåľº
    0.09
    æĮĸæİĺ
    0.09
    èĢģ乡
    0.09
    çŃ¹å»º
    0.08
    uju
    0.08
    漫
    0.08
    Activations Density 0.031%

    No Known Activations