© 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. 61986
    Prev
    Next
    INDEX
    Explanations

    belfast, ireland

    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
    æĻļé¥Ń
    -0.10
     dimensional
    -0.10
    ç´¢åıĸ
    -0.09
    åĭĥåĭĥ
    -0.09
    ä½ĵåĪ¶
    -0.09
    澧
    -0.09
    ems
    -0.09
    ä¸Ĭæµ·
    -0.09
    溥
    -0.09
    说çļĦè¯Ŀ
    -0.09
    POSITIVE LOGITS
     Belfast
    0.11
    ä¸ĢåĪĩ
    0.09
    rew
    0.09
    alan
    0.09
    æݾ
    0.08
    rices
    0.08
    alach
    0.08
    åĩij
    0.08
    reland
    0.08
     Kurdish
    0.08
    Activations Density 0.033%

    No Known Activations