© 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. 35143
    Prev
    Next
    INDEX
    Explanations

    agronomic, agribusiness

    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
    iever
    -0.09
    æĥŁ
    -0.09
    说å®ŀ
    -0.09
    /cgi
    -0.09
    åİŁåŀĭ
    -0.09
    кÑĢо
    -0.08
    ×ķת
    -0.08
    лÑĥ
    -0.08
    lke
    -0.08
    大大å°ıå°ı
    -0.08
    POSITIVE LOGITS
    istory
    0.10
    æľĭåıĭ们
    0.08
    quip
    0.08
    ä»Ĺ
    0.08
    çĨŁ
    0.08
    ниÑĩ
    0.08
    yard
    0.08
    perature
    0.08
    ebra
    0.08
    uman
    0.08
    Activations Density 0.016%

    No Known Activations