© 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. 26562
    Prev
    Next
    INDEX
    Explanations

    Plymouth and Thanksgiving

    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
    鬣
    -0.11
    гад
    -0.09
    å¦
    -0.09
    åħ±äº§åħļåijĺ
    -0.09
    æĪĸå¤ļ
    -0.09
     ведÑĮ
    -0.09
    sumer
    -0.09
    icultural
    -0.09
    pref
    -0.08
    egration
    -0.08
    POSITIVE LOGITS
    dom
    0.09
    åı¸
    0.09
    åĩĮ
    0.09
    forth
    0.08
    fon
    0.08
    èµĦæºIJéħįç½®
    0.08
    åįģæľĪ
    0.08
    æĮŁ
    0.08
    eld
    0.08
    unn
    0.08
    Activations Density 0.007%

    No Known Activations