© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37416
    Prev
    Next
    INDEX
    Explanations

    seems adjective enough/to

    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
    éľĦ
    -0.10
    Ñģад
    -0.09
    Shown
    -0.09
     Clyde
    -0.09
    æĢ¨
    -0.08
    çŃĮ
    -0.08
     Rao
    -0.08
    inge
    -0.08
    åħ¬è®¤çļĦ
    -0.08
    adies
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.10
    ä¼¼çļĦ
    0.09
     dood
    0.09
    欣æħ°
    0.09
    åīįä¸ĸ
    0.08
    好åĥı
    0.08
    æľīå¿ħè¦ģ
    0.08
    éģ¥
    0.08
     somehow
    0.08
    ä¼¼ä¹İ
    0.08
    Activations Density 0.050%

    No Known Activations