© 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. 34079
    Prev
    Next
    INDEX
    Explanations

    triathlon, Ironman, heptathlon

    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
    åĩłåı¥
    -0.11
    éľĨ
    -0.10
    Mit
    -0.09
    رÙħ
    -0.09
    对æĬĹ
    -0.09
    ivot
    -0.09
    ä¸įå°½
    -0.09
    çĺIJ
    -0.09
     Mit
    -0.09
    ä¾Ŀçħ§
    -0.09
    POSITIVE LOGITS
    urus
    0.08
    -type
    0.08
    åĨħå¤ĸ
    0.08
    ç»ı纬
    0.08
    æ°¸åĪ©
    0.08
    ä¹Ŀå·ŀ
    0.08
     Dtype
    0.08
    orous
    0.08
    SetUp
    0.07
    plex
    0.07
    Activations Density 0.012%

    No Known Activations