© 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. 11466
    Prev
    Next
    INDEX
    Explanations

    illustrations, artwork, and design

    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
    kie
    -0.10
    _TestCase
    -0.10
    ä½ľåĵģåĨħ容
    -0.10
     Hoffman
    -0.10
     hÆ°á»Łng
    -0.10
    ç½ijéĢļ
    -0.10
    æĢĿç´¢
    -0.09
    èĢĥãģĪãĤĭ
    -0.09
    azio
    -0.09
    ansa
    -0.09
    POSITIVE LOGITS
     shrink
    0.09
    pd
    0.09
    èķŀ
    0.08
    纯
    0.08
    åĽŀæļĸ
    0.08
    åłķ
    0.08
    _MAXIMUM
    0.08
    y
    0.08
    çĶµçº¿
    0.07
    羣çĪ±
    0.07
    Activations Density 0.115%

    No Known Activations