© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10545
    Prev
    Next
    INDEX
    Explanations

    Greenwich and London place names

    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
    ominated
    -0.09
    amental
    -0.09
    åīįæīĢ
    -0.09
    ossa
    -0.09
    educt
    -0.09
    icing
    -0.08
    oload
    -0.08
    Äı
    -0.08
    è¿ĩåħ³
    -0.08
    uctions
    -0.08
    POSITIVE LOGITS
    ÙĬات
    0.09
    ÑĮ
    0.08
    ãĥ³ãĤ°
    0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    0.08
    -Bar
    0.08
    borg
    0.08
    è°¨
    0.08
     Hoy
    0.08
    lc
    0.08
    åŁİ乡å±ħæ°ij
    0.08
    Activations Density 0.002%

    No Known Activations