© 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. 18006
    Prev
    Next
    INDEX
    Explanations

    charity or organization name

    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
    主æĦı
    -0.11
    饱满
    -0.09
     intim
    -0.08
    thouse
    -0.08
    åijĬ
    -0.08
    çªĪ
    -0.08
     Wheeler
    -0.08
    _gb
    -0.08
    æijĶåĢĴ
    -0.08
     зай
    -0.08
    POSITIVE LOGITS
    å¡ijèĥ¶
    0.10
    .addObject
    0.09
    ä¼ģä¸ļæĸĩåĮĸ
    0.09
    éĥ¦
    0.09
     buc
    0.09
    .GetObject
    0.09
    åIJĥé¥Ń
    0.09
     Playboy
    0.09
    æĨ¨
    0.09
    åĩºèµĦ
    0.09
    Activations Density 0.100%

    No Known Activations