© 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. 18611
    Prev
    Next
    INDEX
    Explanations

    'm or you're followed by verb

    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
    è¿Ħä»Ĭ为æŃ¢
    -0.11
    ,ep
    -0.09
    uae
    -0.09
    ä»Ĭ天çļĦ
    -0.09
    æIJº
    -0.09
    询
    -0.09
    çİ°åľ¨çļĦ
    -0.08
    å¾®è§Ĥ
    -0.08
    èĩ³ä»Ĭ
    -0.08
    AYER
    -0.08
    POSITIVE LOGITS
    å½·
    0.09
    åĮħ袱
    0.09
    allee
    0.09
    æķ´çIJĨ
    0.09
    梳çIJĨ
    0.09
    æģģ
    0.08
    æĸľ
    0.08
    æĦı大
    0.08
    çĸij
    0.08
    æĭ¼
    0.08
    Activations Density 0.042%

    No Known Activations