© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9762
    Prev
    Next
    INDEX
    Explanations

    specific numbers or quantities

    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
    å¯ĵæĦı
    -0.09
    .frames
    -0.09
    满æĢĢ
    -0.09
    UsageId
    -0.09
    _utilities
    -0.08
    èĤ¤
    -0.08
    ạng
    -0.08
    íħľ
    -0.08
    æĽĻ
    -0.08
    eldon
    -0.08
    POSITIVE LOGITS
    éĩĩçĶ¨äºĨ
    0.12
    åĨħç½®
    0.11
    æľīèĩªå·±çļĦ
    0.10
     internal
    0.10
    çĭ¬ç«ĭ
    0.09
    åIJİåı°
    0.09
    æł¸å¿ĥæĬĢæľ¯
    0.09
    强大çļĦ
    0.09
    è´¯
    0.09
    çį¨ç«ĭ
    0.09
    Activations Density 0.359%

    No Known Activations