© 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. 16197
    Prev
    Next
    INDEX
    Explanations

    lobbying and influence

    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
    å½ĵå±Ģ
    -0.23
    åĪĽéĢłæĢ§
    -0.20
    ÅŁÄ±
    -0.20
    å½ĵåľ°æĶ¿åºľ
    -0.20
    ä¿®åħ»
    -0.20
    æŁ¥éªĮ
    -0.19
    Authorities
    -0.19
     اÙĦÙĦا
    -0.19
    åıįæĢĿ
    -0.19
    åĪ«äººçļĦ
    -0.19
    POSITIVE LOGITS
     influence
    0.27
     lobbyists
    0.25
     Influence
    0.24
    canf
    0.23
     lobby
    0.23
    coal
    0.22
    lobby
    0.22
     influences
    0.22
     coal
    0.21
     lobbying
    0.21
    Activations Density 0.019%

    No Known Activations