© 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. 48024
    Prev
    Next
    INDEX
    Explanations

    Holland / Hollande / Dutch place names and people

    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
     Hick
    -0.10
    ../../
    -0.10
    ÙĪر
    -0.09
    IMUM
    -0.09
    ingly
    -0.09
    们
    -0.09
    ilm
    -0.08
    ãĤ£
    -0.08
    å¿ĥ头
    -0.08
    çĮ¬
    -0.08
    POSITIVE LOGITS
    sworth
    0.12
    aise
    0.12
    à¹Į
    0.10
    媳
    0.10
    ale
    0.10
    anness
    0.09
    tron
    0.09
    oney
    0.09
    /or
    0.09
    alem
    0.09
    Activations Density 0.018%

    No Known Activations