© 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. 33500
    Prev
    Next
    INDEX
    Explanations

    travel and shipping

    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
    bast
    -0.09
    泺
    -0.09
    ATO
    -0.09
    å§Ŀ
    -0.09
     Indo
    -0.08
    .lu
    -0.08
    angu
    -0.08
    æµ´
    -0.08
    avar
    -0.08
    esan
    -0.08
    POSITIVE LOGITS
    è°Ħ
    0.09
    æĿ¥çļĦ
    0.09
    èĮ¬
    0.08
    à¸Ļà¸Ħร
    0.08
    rox
    0.08
    ãģĭãĤīãģ¯
    0.08
    åIJĦçľģ
    0.08
    ä¸Ńå°ı
    0.08
    anza
    0.08
    è¿ĩæĿ¥
    0.08
    Activations Density 0.020%

    No Known Activations