© 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. 53730
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    åĽŀåİ»
    -0.10
    åģļçļĦäºĭæĥħ
    -0.09
    å±ĬæŶ
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.08
    lage
    -0.08
    æĦıè§ģ
    -0.08
    æīĢæľīçļĦ
    -0.08
    Documents
    -0.08
     Madden
    -0.08
    åĬŀäºĭ
    -0.08
    POSITIVE LOGITS
    åħ¬å¼Ģåıijè¡Į
    0.10
    åħ¬ç¤º
    0.09
    hdr
    0.08
    ListOf
    0.08
    wise
    0.08
    å¼ĢæºIJ
    0.08
     officially
    0.08
    罡
    0.08
    brace
    0.08
    igest
    0.08
    Activations Density 0.065%

    No Known Activations