© 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. 38236
    Prev
    Next
    INDEX
    Explanations

    AFC teams and sports leagues

    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
    ifax
    -0.10
    atives
    -0.10
    sti
    -0.09
    cole
    -0.09
     пÑıÑĤ
    -0.09
    尽头
    -0.09
    letic
    -0.09
    ãĤ£
    -0.09
     ÑħозÑıйÑģÑĤв
    -0.08
    arshal
    -0.08
    POSITIVE LOGITS
    uous
    0.09
    ypes
    0.09
    اعة
    0.09
    akis
    0.08
    ä¹IJè§Ĥ
    0.08
    æĸ°åĮº
    0.08
     conserv
    0.08
    ias
    0.08
    icas
    0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.08
    Activations Density 0.005%

    No Known Activations