© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    Sounders FC

    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
    æĻ·
    -0.10
    TING
    -0.09
     cork
    -0.08
    亲
    -0.08
    æľī人
    -0.08
    apesh
    -0.08
    æı£
    -0.08
    åijķåIJIJ
    -0.08
     Gors
    -0.08
    æľīçļĦ
    -0.08
    POSITIVE LOGITS
    ertest
    0.11
    ers
    0.11
    nock
    0.10
     maiden
    0.09
    ful
    0.09
    hill
    0.09
    erm
    0.09
    éĿŀ常æĺİæĺ¾
    0.09
    éĿŀåĩ¡
    0.09
    villa
    0.09
    Activations Density 0.008%

    No Known Activations