© 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. 15992
    Prev
    Next
    INDEX
    Explanations

    violence and violent behavior

    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
    åŃIJéĩĮ
    -0.20
    ivers
    -0.19
    ¤í
    -0.17
    ãģĦãĤĭ
    -0.17
    .masks
    -0.17
     bè
    -0.17
    scription
    -0.17
    èĢģ人家
    -0.17
    ÑģÑĤо
    -0.16
    traction
    -0.16
    POSITIVE LOGITS
    -minded
    0.21
    -hearted
    0.20
     minded
    0.20
    emente
    0.17
    æĢ§å¼º
    0.17
    -packed
    0.16
    etty
    0.16
    ãģĹãĤĩãģĨ
    0.16
    jin
    0.16
    esis
    0.16
    Activations Density 0.010%

    No Known Activations