© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5380
    Prev
    Next
    INDEX
    Explanations

    lobbying and influence efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    mand
    -0.10
    éĵ¡
    -0.09
    .gnu
    -0.09
    åIJĮåŁİ
    -0.09
    ç¼ĵ解
    -0.09
    eroon
    -0.09
    /libs
    -0.09
    æĤŁ
    -0.09
    åī²
    -0.09
    å§Ĭ
    -0.09
    POSITIVE LOGITS
    lobby
    0.11
     Lobby
    0.11
    äºīåıĸ
    0.11
     lobby
    0.10
     strategy
    0.08
     lobbyists
    0.08
     lobbying
    0.08
     influence
    0.08
    tl
    0.08
    æĥ®
    0.08
    Activations Density 0.059%

    No Known Activations