© 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. 50812
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones

    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
    é¹Ħ
    -0.10
    ä¸įåıĬ
    -0.09
    åĭ¿
    -0.09
    иÑĢ
    -0.09
    åģļ个
    -0.08
    aan
    -0.08
     pare
    -0.08
    æ³Ħ
    -0.08
    .ht
    -0.08
    åŁİå¸Ĥåıijå±ķ
    -0.08
    POSITIVE LOGITS
    çħ¨
    0.10
    ilon
    0.09
    åIJģ
    0.09
    åħ¨ç¨ĭ
    0.09
    æĿĸ
    0.08
    åħ¥å¢ĥ
    0.08
    metis
    0.08
     recreated
    0.08
    éĩį建
    0.08
    inati
    0.08
    Activations Density 0.012%

    No Known Activations