© 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. 1519
    Prev
    Next
    INDEX
    Explanations

    coastal, sea, ocean

    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
     anonymous
    -0.09
    Jvm
    -0.09
     Yellowstone
    -0.09
    çľī
    -0.09
    ä¾Ŀæ³ķ
    -0.09
    éļĭ
    -0.09
    lyph
    -0.08
    -android
    -0.08
    æĺ¯æĪijçļĦ
    -0.08
    大çģ«
    -0.08
    POSITIVE LOGITS
     Calder
    0.10
    æµ·æ¹¾
    0.10
    æµ·æ´ĭ
    0.10
    樯
    0.10
    海滨
    0.10
    æµ·åı£
    0.10
    å¾Īæ£Ĵ
    0.09
    antino
    0.09
     ming
    0.09
    海岸
    0.09
    Activations Density 0.148%

    No Known Activations