© 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. 54641
    Prev
    Next
    INDEX
    Explanations

    below or above a threshold

    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
    è¯Ŀ说
    -0.11
    çĵ¶åŃIJ
    -0.10
    perature
    -0.09
    èİľ
    -0.09
    .ObjectModel
    -0.09
    еÑĢÑĮ
    -0.09
    éĩijåŃĹ
    -0.09
    ucker
    -0.09
    adesh
    -0.09
    祸
    -0.09
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.11
    åİŁæľīçļĦ
    0.09
    -than
    0.09
    ope
    0.09
    ey
    0.08
    éĤ£ä¸Ģ
    0.08
    ä»Ģä¹Īåij¢
    0.08
    Beh
    0.08
    est
    0.08
    ä¼łç»Ł
    0.08
    Activations Density 0.018%

    No Known Activations