© 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. 17810
    Prev
    Next
    INDEX
    Explanations

    star clusters

    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
    åľĪ
    -0.09
    бил
    -0.09
    ãĥĽãĥ¼ãĥłãĥļãĥ¼ãĤ¸
    -0.09
    åŀ©
    -0.09
    纲
    -0.09
    .descriptor
    -0.08
    è¡Ļ
    -0.08
    urt
    -0.08
     trilogy
    -0.08
     unl
    -0.08
    POSITIVE LOGITS
    éĽĨ群
    0.10
    工人
    0.09
    æĵģ
    0.09
    VB
    0.09
    æīįç®Ĺ
    0.09
    æĪIJåijĺ
    0.09
    å¹»æĥ³
    0.09
    群
    0.09
    éĻĦè¿ijçļĦ
    0.08
    èľĤèľľ
    0.08
    Activations Density 0.190%

    No Known Activations