© 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. 61367
    Prev
    Next
    INDEX
    Explanations

    golf related terms and scoring

    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
    穹
    -0.09
    çĥģ
    -0.09
    æIJľ
    -0.09
    鸡èĤī
    -0.09
    款
    -0.08
    åħ¹
    -0.08
    regon
    -0.08
    ĥģ
    -0.08
    èĤ¢
    -0.08
    alic
    -0.08
    POSITIVE LOGITS
    æķ°æį®æĺ¾ç¤º
    0.09
    éĤĵå°ı
    0.08
    åij¨æģ©
    0.08
    éĤĵå°ıå¹³
    0.08
    SetUp
    0.08
    âĪ
    0.08
     progressives
    0.08
    èı½
    0.08
    çī¹æľĹ
    0.08
    .Listener
    0.08
    Activations Density 0.009%

    No Known Activations