© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12415
    Prev
    Next
    INDEX
    Explanations

    campaign, goal, or required funding

    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
    ãģ¡ãĤĥãĤĵãģ¨
    -0.20
    phia
    -0.18
     outside
    -0.18
    é¦Ĺ
    -0.18
    /rss
    -0.18
     reb
    -0.18
     Earn
    -0.17
    åŃĺè´§
    -0.17
    Earn
    -0.17
    ä¹¡åľŁ
    -0.17
    POSITIVE LOGITS
    缮æłĩ
    0.28
    ä¸į足
    0.26
    çŃ¹éĽĨ
    0.25
     campaign
    0.24
    åĭŁéĽĨ
    0.24
    çļĦ缮æłĩ
    0.24
    æīĢéľĢè¦ģçļĦ
    0.23
     goal
    0.23
     needed
    0.23
    缮æ¨Ļ
    0.22
    Activations Density 0.015%

    No Known Activations