© 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. 28110
    Prev
    Next
    INDEX
    Explanations

    champion or winner

    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
    ä¸Ģå¦Ĥ
    -0.09
    家åĸ»æĪ·æĻĵ
    -0.08
    ä¸ĢåIJį
    -0.08
    ourt
    -0.08
     Zac
    -0.08
    1
    -0.08
    éĤ£ä¹Ī容æĺĵ
    -0.08
    å¢ŀ
    -0.08
    ered
    -0.08
    大æĪĺ
    -0.08
    POSITIVE LOGITS
    ems
    0.11
    æµ·éĩı
    0.09
    毫
    0.09
    Ãłng
    0.09
    engl
    0.08
     Mah
    0.08
    ÃľR
    0.08
    åĢij
    0.08
    anel
    0.08
    示èĮĥåĮº
    0.08
    Activations Density 0.022%

    No Known Activations