© 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. 33094
    Prev
    Next
    INDEX
    Explanations

    first person auxiliary verbs

    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
    çIJĨ解åĴĮ
    -0.13
    æľįåĬ¡
    -0.10
    ä¹Łè®©
    -0.09
    好æ¶Īæģ¯
    -0.08
    WithPath
    -0.08
    ruptions
    -0.08
    ãĤĤãģ£ãģ¨
    -0.08
    建设åĴĮ
    -0.08
    æ¯ıä¸Ģä½į
    -0.08
    머
    -0.08
    POSITIVE LOGITS
    åĽłèĢĮ
    0.11
     consequently
    0.11
    /or
    0.11
    å¾Ĺ以
    0.11
    åĽłæѤ
    0.11
    ä¸įå¾Ĺä¸į
    0.11
     therefore
    0.11
    8
    0.10
    5
    0.10
    éļıä¹ĭ
    0.10
    Activations Density 0.271%

    No Known Activations