© 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. 13109
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

    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
    人æ°Ķ
    -0.21
    _slave
    -0.21
    é¢Ī
    -0.20
    èį¡
    -0.19
    çij¾
    -0.19
    apo
    -0.18
     занÑıÑĤ
    -0.18
    ARN
    -0.18
    anager
    -0.17
    TextNode
    -0.17
    POSITIVE LOGITS
     пÑĢоиÑģ
    0.24
    åīįä¸ĸ
    0.21
    onde
    0.21
    _GC
    0.20
    èĮĦ
    0.19
    空æ°Ķ
    0.19
    lian
    0.18
    å¾Ģè¿Ķ
    0.18
    à¹Ģà¸Ĥ
    0.18
    èĭ¦
    0.17
    Activations Density 0.379%

    No Known Activations