© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29552
    Prev
    Next
    INDEX
    Explanations

    craftian, organic phosphate, valence

    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
    Negative Logits
    åĽŀäºĭ
    -0.09
    åĪĢ
    -0.09
    è°Ĭ
    -0.09
    å¦ĤæĦı
    -0.08
    ³
    -0.08
    rek
    -0.08
     intr
    -0.08
    çľĭä¸įåĩº
    -0.08
     promises
    -0.08
    ç«
    -0.07
    POSITIVE LOGITS
    èĥ¸æĢĢ
    0.10
    åij¨è½¬
    0.09
    é¬ĵ
    0.09
    ::.
    0.09
    IGIN
    0.09
    coder
    0.09
     treÅĽci
    0.09
    ê¸ī
    0.08
    缸æ¯Ķä¹ĭä¸ĭ
    0.08
    çĦļ
    0.08
    Activations Density 0.011%

    No Known Activations