© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    government subsidies and incentives

    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
    åĽ¢åľĨ
    -0.21
    åĪ©çĶ¨æĤ¨çļĦ
    -0.20
    ä»İ严治
    -0.20
     Wich
    -0.20
    ç»ıéªĮåĴĮ
    -0.19
    精彩çļĦ
    -0.19
     оÑĤдÑĭÑħ
    -0.19
    yre
    -0.19
    åĽ¢
    -0.18
    个æĢ§
    -0.18
    POSITIVE LOGITS
    æī¶æĮģ
    0.29
    ä¿ĥæĪIJ
    0.24
    æī¶
    0.23
    èµĦåĬ©
    0.23
    åĬłæĮģ
    0.22
    itals
    0.21
    å¼ķ导
    0.20
     pref
    0.20
    æĶ¯æĴij
    0.20
    æĶ¯æĮģ
    0.19
    Activations Density 0.010%

    No Known Activations