© 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. 58174
    Prev
    Next
    INDEX
    Explanations

    airplanes and aircraft

    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
    æŀ£
    -0.09
    çIJĨçĶ±
    -0.09
    swer
    -0.09
    aad
    -0.09
    æł´
    -0.08
    ä¸įåłª
    -0.08
    uder
    -0.08
    dain
    -0.08
    ãĥ¼ãĤ¹
    -0.08
    çĭĤ欢
    -0.08
    POSITIVE LOGITS
    é£ŀæľº
    0.18
    æľºåľº
    0.16
    âľĪ
    0.15
    é£ŀè¡Į
    0.14
     airplane
    0.13
    èĪªçıŃ
    0.13
    æ°ijèĪª
    0.13
    æĪĺæľº
    0.13
     Aircraft
    0.13
     airplanes
    0.13
    Activations Density 0.141%

    No Known Activations