© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    Chesapeake Bay ecosystem restoration

    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
    æĸ¹å¼ı
    -0.21
    åľ°éľĩ
    -0.20
     Meteor
    -0.20
    æĶĢ
    -0.20
    Meteor
    -0.20
    æ¡ī
    -0.19
    碾
    -0.19
    ollo
    -0.19
    庸
    -0.19
    launcher
    -0.19
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.24
    çĶŁæĢģçݯå¢ĥ
    0.22
    çĬ¶åĨµ
    0.22
    ä¿ĿèŃ·
    0.21
    çݯå¢ĥä¿ĿæĬ¤
    0.21
    管çIJĨèĢħ
    0.21
     steward
    0.21
    çĽijæµĭ
    0.21
    æĶ¹åĸĦ
    0.21
     protections
    0.21
    Activations Density 0.041%

    No Known Activations