© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12856
    Prev
    Next
    INDEX
    Explanations

    Indian infantry brigade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     hurd
    -0.24
    vit
    -0.24
    çĶľèľľ
    -0.22
    好äºĭ
    -0.21
    æ°´æĻ¶
    -0.20
    æİ¥å¾ħ
    -0.20
     spiked
    -0.20
     viol
    -0.19
    Chair
    -0.19
    orio
    -0.19
    POSITIVE LOGITS
    ç»ĦæĪIJçļĦ
    0.34
    ç»ĦæĪIJ
    0.31
    人æķ°
    0.29
    ç»Ħ建
    0.27
    åĬĽéĩı
    0.27
    éĺŁä¼į
    0.25
    rons
    0.24
    æĪĺæĸĹåĬĽ
    0.24
    主åĬĽ
    0.23
    è§Ħ模
    0.23
    Activations Density 0.063%

    No Known Activations