© 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. 4629
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or "self"

    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
    ç»Ļ人ä¸Ģç§į
    -0.11
    è¿Ļä¹Łæĺ¯
    -0.10
    åIJijçĿĢ
    -0.10
    è¦ģæĬĬ
    -0.09
    让æĪij们
    -0.09
    马ä¸Ĭå°±
    -0.09
    æĪIJåĬŁçİĩ
    -0.09
    spent
    -0.09
    è®©æĽ´å¤ļ
    -0.09
    æĪij们ä¸Ģèµ·
    -0.08
    POSITIVE LOGITS
    zelf
    0.12
    æĵį
    0.10
    /her
    0.10
    ials
    0.09
    æªĢ
    0.09
    /he
    0.09
    self
    0.08
    æīĢèĥ½
    0.08
    -même
    0.08
    é¢ĵ
    0.08
    Activations Density 0.162%

    No Known Activations