© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36715
    Prev
    Next
    INDEX
    Explanations

    people or places named Williams

    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
    ftware
    -0.12
    è¯Ŀ说
    -0.11
    fully
    -0.10
    èĥĽ
    -0.10
    缨
    -0.10
    uary
    -0.10
    ting
    -0.10
    ption
    -0.09
    ÑĩаÑĤ
    -0.09
    æĦĨ
    -0.09
    POSITIVE LOGITS
    urve
    0.10
    ieur
    0.10
    loth
    0.09
    urse
    0.09
    reuse
    0.09
    erin
    0.08
     Rubio
    0.08
    isas
    0.08
    squ
    0.08
    urst
    0.08
    Activations Density 0.032%

    No Known Activations