© 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. 34374
    Prev
    Next
    INDEX
    Explanations

    Chinese dynasties

    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
    åŁĥå°Ķ
    -0.10
    éĹ·
    -0.09
    _Utils
    -0.09
    èħĵ
    -0.09
    åݦ
    -0.09
    æĭīæĸ¯
    -0.08
    æ¸łéģĵ
    -0.08
    igy
    -0.08
    Kin
    -0.08
    ieber
    -0.08
    POSITIVE LOGITS
    æľĿå»·
    0.10
    å®ĺ
    0.10
    å®ĺåijĺ
    0.10
    è±¢
    0.09
    æľ«
    0.09
    奸
    0.09
    宵
    0.09
     dynasty
    0.09
    大å®Ĺ
    0.09
    éĢīæĭĶ
    0.09
    Activations Density 0.045%

    No Known Activations