© 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. 57233
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    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
    å±ıå¹ķä¸Ĭ
    -0.09
    ovich
    -0.09
    tal
    -0.09
     tal
    -0.09
     Lif
    -0.09
    ãĤīãģĦ
    -0.09
    å±ı
    -0.09
    çĬ¶åĨµ
    -0.08
    éĽªå±±
    -0.08
    rats
    -0.08
    POSITIVE LOGITS
    æĭ³
    0.09
    è¿Ļå¼ł
    0.09
    çľī
    0.08
    æİ°
    0.08
    举è¡ĮçļĦ
    0.08
    天æĸĩ
    0.08
    ä¸įå°ıå¿ĥ
    0.08
    常德
    0.08
    iram
    0.08
    çĺķ
    0.08
    Activations Density 0.146%

    No Known Activations