© 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. 31199
    Prev
    Next
    INDEX
    Explanations

    pondering and questioning

    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
    èĥ½åģļåĪ°
    -0.09
     sı
    -0.09
    åĮį
    -0.09
    çĨ¬
    -0.09
    èij³
    -0.09
    çıĤ
    -0.09
    导è´Ń
    -0.08
     Happ
    -0.08
    迹
    -0.08
    建åįİ
    -0.08
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.15
    åıįæĢĿ
    0.13
     reconsider
    0.13
    èĢĥèĻij
    0.13
     rethink
    0.12
    åıįçľģ
    0.12
    è¦ģèĢĥèĻij
    0.11
    ãĤĴèĢĥãģĪ
    0.11
     ponder
    0.10
    åĽŀåij³
    0.10
    Activations Density 0.031%

    No Known Activations