© 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. 16304
    Prev
    Next
    INDEX
    Explanations

    health-related videos

    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
     fetisch
    -0.24
     erotisk
    -0.24
     execution
    -0.24
    溷
    -0.24
     ÑĦоÑĢмиÑĢова
    -0.23
    åĩĨæŶ
    -0.21
    благо
    -0.21
    çŁ¿
    -0.21
     realised
    -0.20
    execution
    -0.20
    POSITIVE LOGITS
    ç§ijæĻ®
    0.31
    åģ¥åº·
    0.26
    å°±è¯Ĭ
    0.25
    åĮ»åѦ
    0.23
    æĤ£èĢħ
    0.23
    çŃĽæŁ¥
    0.23
    ä»ħä¾ĽåıĤèĢĥ
    0.22
    ä»ħä¾Ľ
    0.22
    _HEALTH
    0.22
     medical
    0.21
    Activations Density 0.092%

    No Known Activations