© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    lobby, corporations, tobacco, fuel, trust

    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
    arella
    -0.09
    аÑĨион
    -0.09
    大è¡Ĺ
    -0.09
    ä¸Ģé¢Ĺ
    -0.09
    æĢ»éĺŁ
    -0.08
    .Drop
    -0.08
    åŃļ
    -0.08
    çĵł
    -0.08
    åĶ¾
    -0.08
    æĶ¯éĺŁ
    -0.08
    POSITIVE LOGITS
    åĪ©çĽĬ
    0.14
     interests
    0.13
    çļĦåĪ©çĽĬ
    0.12
    ingu
    0.10
    ķĮ
    0.10
    åĬ¿åĬĽ
    0.09
    æİ£
    0.09
    éĺ»åĬĽ
    0.09
    大佬
    0.09
    æĬĬæĮģ
    0.09
    Activations Density 0.062%

    No Known Activations