© 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. 22522
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

    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
    峡
    -0.10
    åŁİ乡
    -0.10
    æĶ«
    -0.10
    åħ¨æ°ij
    -0.09
     auss
    -0.09
    æĭĩæĮĩ
    -0.09
    橱
    -0.09
    åijĪçİ°åĩº
    -0.09
    ked
    -0.09
    INK
    -0.09
    POSITIVE LOGITS
    fr
    0.09
    è¡®
    0.08
    å¾·å·ŀ
    0.08
    oline
    0.08
     lesser
    0.07
     Lesser
    0.07
    åĬ±
    0.07
    æĸ°äºº
    0.07
    ä¸Ńéĥ¨
    0.07
    å¬ī
    0.07
    Activations Density 0.173%

    No Known Activations