© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37024
    Prev
    Next
    INDEX
    Explanations

    Erlang, Emirates, Scotch, Bombay

    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
    éĺ²èħIJ
    -0.09
    regation
    -0.09
    ç¡IJ
    -0.08
    otos
    -0.08
    GY
    -0.08
    azon
    -0.08
    uration
    -0.08
    cape
    -0.08
     dụng
    -0.08
     اÙĦجÙħÙĩ
    -0.08
    POSITIVE LOGITS
    bred
    0.12
    pu
    0.11
    gether
    0.11
    pare
    0.09
    boarding
    0.09
    çijľ
    0.09
    çĺ¾
    0.09
    åºij
    0.09
    ness
    0.09
    羯
    0.09
    Activations Density 0.005%

    No Known Activations