© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns before nouns

    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
     ÙħÙĤابÙĦ
    -0.09
    åĩłä¹İ
    -0.08
    åıªè¦ģä½ł
    -0.08
    Ñģкоп
    -0.08
    å±ħçĦ¶
    -0.08
    èĻ½çĦ¶
    -0.08
    æ°¸ä¸į
    -0.08
    аÑĤ
    -0.08
     наиболее
    -0.08
    æĭĵ
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.09
    èĤ¾èĦı
    0.08
    /do
    0.08
    ç¡®
    0.08
    æľºä½ĵ
    0.08
    好äºĭ
    0.08
     ÃŃch
    0.08
    ington
    0.08
    )))),
    0.08
     golf
    0.08
    Activations Density 0.092%

    No Known Activations