© 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. 13470
    Prev
    Next
    INDEX
    Explanations

    leaks and classified documents

    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
     обÑĥÑĩениÑı
    -0.20
    ç¥ł
    -0.20
    ç¬ij声
    -0.18
     дизайн
    -0.18
    综åIJĪæ²»çIJĨ
    -0.18
    硼
    -0.17
    earch
    -0.17
    ä¸Ģ楼
    -0.17
    à¤Ń
    -0.17
    .Toolkit
    -0.17
    POSITIVE LOGITS
    åħ¬å¼Ģ
    0.22
    ocene
    0.20
    ico
    0.20
    大éĩı
    0.20
    çĪĨæĸĻ
    0.19
    æľī大éĩıçļĦ
    0.19
    acci
    0.19
    ç¢İçīĩ
    0.18
    社ä¼ļç»Ħç»ĩ
    0.18
    .dump
    0.18
    Activations Density 0.005%

    No Known Activations