© 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. 57152
    Prev
    Next
    INDEX
    Explanations

    children and kids

    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
    åŃķ
    -0.10
    çħĻ
    -0.10
    åĵ¨
    -0.09
    ä¸Ģ份
    -0.09
    äºĨä¸Ģ份
    -0.09
    éĢĴç»Ļ
    -0.09
    åıĸèĥľ
    -0.09
    è´©
    -0.09
    ikers
    -0.09
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    POSITIVE LOGITS
    çļĦæĪIJéķ¿
    0.09
    åĦ¿å¥³
    0.09
    åŃIJ女
    0.09
     Donovan
    0.09
    åĿļ强
    0.09
    å¾Ģäºĭ
    0.09
    åıĽ
    0.08
    æ±Łå±±
    0.08
    jos
    0.08
    .stub
    0.08
    Activations Density 0.065%

    No Known Activations