© 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. 11875
    Prev
    Next
    INDEX
    Explanations

    saving life

    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
    åħ»èĢģéĩij
    -0.21
    å¨ĺ家
    -0.20
    orph
    -0.19
    åģľçĶµ
    -0.19
     elabor
    -0.18
    åIJĦèĩª
    -0.18
    åģ¶
    -0.17
     sqr
    -0.17
    æĹ¥åŃIJ
    -0.17
    ä¸įçĶ¨æĭħå¿ĥ
    -0.17
    POSITIVE LOGITS
    -threatening
    0.24
    æĮ½åĽŀ
    0.21
    æĢ§åij½
    0.21
    itaire
    0.20
    å²Į
    0.20
    åį±
    0.19
    ardy
    0.19
    çĿĩ
    0.19
    akes
    0.19
    atham
    0.18
    Activations Density 0.026%

    No Known Activations