© 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. 19203
    Prev
    Next
    INDEX
    Explanations

    election votes and issues

    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
    ensis
    -0.09
    strup
    -0.09
     ÑģовÑģем
    -0.08
    æľ¬ç½ij
    -0.08
    å¼ķ
    -0.08
    交æµģåIJĪä½ľ
    -0.08
    eni
    -0.08
    è´¹çİĩ
    -0.08
     boyc
    -0.08
    _least
    -0.08
    POSITIVE LOGITS
    åħļ
    0.12
    åħijçİ°
    0.11
     паÑĢÑĤи
    0.10
    è¿İåIJĪ
    0.10
    æ°ijæĦı
    0.09
    å¾Ĺ罪
    0.09
     ÑĢеÑĪи
    0.09
    æī§æĶ¿
    0.09
    稳
    0.09
    解åĨ³äºĨ
    0.09
    Activations Density 0.097%

    No Known Activations