© 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. 11599
    Prev
    Next
    INDEX
    Explanations

    violence and human rights abuses

    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
    æı¡
    -0.23
    åħīèĬĴ
    -0.23
    å®ĥçļĦ
    -0.21
    ç¾İåѦ
    -0.21
    ä»ĸçļĦ
    -0.20
    æŁIJç§į
    -0.20
    æĺİ亮
    -0.20
    帮ä»ĸ
    -0.20
    åİŁåŀĭ
    -0.20
    è·Łä»ĸ
    -0.20
    POSITIVE LOGITS
    ikel
    0.23
    çĶļèĩ³
    0.22
    æ²Ń
    0.22
    éļĺ
    0.21
    ieux
    0.20
     ÑģлÑĥÑĩа
    0.20
    ieg
    0.20
     Nah
    0.20
    ometimes
    0.20
    esian
    0.19
    Activations Density 0.028%

    No Known Activations