© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    fiscal cliff deal cuts tariffs fines

    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
    à¸Ńà¸ļ
    -0.22
    趾
    -0.22
    æµ·æĬ¥
    -0.20
    è¡ĢèĦī
    -0.19
     Decoration
    -0.19
    å½ĵåľº
    -0.19
     rá
    -0.19
    èį·
    -0.19
    çĥŃ线
    -0.19
    æ¸ĶèĪ¹
    -0.19
    POSITIVE LOGITS
    æľºåĪ¶
    0.25
     mechanisms
    0.23
     mechanism
    0.22
     provisions
    0.21
    åĢĴ
    0.20
    触åıij
    0.19
    fter
    0.19
    ctions
    0.18
    trigger
    0.18
    OFF
    0.18
    Activations Density 0.002%

    No Known Activations