© 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. 10987
    Prev
    Next
    INDEX
    Explanations

    canoeists, luge, fencing, eventing

    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
    æ°´æºIJ
    -0.23
    ç¿Ĵæħ£
    -0.20
    åĭī强
    -0.19
    åįĬæľĪ
    -0.19
    æł¡åĮº
    -0.19
    åĩ¡äºĭ
    -0.19
    æµĵåİļ
    -0.19
    undy
    -0.19
     statewide
    -0.19
    TriState
    -0.19
    POSITIVE LOGITS
    ä¸Ģ项
    0.23
    两项
    0.23
    è¿Ļ项
    0.22
    ä¸ī项
    0.21
    åĽ½éĻħåIJĪä½ľ
    0.21
    æŃ¤é¡¹
    0.21
    alis
    0.21
     opener
    0.21
    elor
    0.21
    å¤§åĽ½
    0.20
    Activations Density 0.090%

    No Known Activations