© 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. 10779
    Prev
    Next
    INDEX
    Explanations

    measurements of children's feet

    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
    纳æĸ¯
    -0.10
    éĢłåŀĭ
    -0.10
     amount
    -0.09
     cont
    -0.09
    reek
    -0.09
    .openg
    -0.09
    é¢Ħ计
    -0.09
    å¸Ĥåľºä»½é¢Ŀ
    -0.08
    èī²
    -0.08
    æĪĺæĸĹåĬĽ
    -0.08
    POSITIVE LOGITS
    åıĤçħ§
    0.11
    æµĭéĩı
    0.09
    éŀ£
    0.09
    æŃ»
    0.09
    èĭ¥å¹²
    0.08
    stat
    0.08
     FAQ
    0.08
    çĶ·å¥³
    0.08
    åħ¬ç¤º
    0.08
    çľ¼è§Ĵ
    0.08
    Activations Density 0.163%

    No Known Activations