© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13836
    Prev
    Next
    INDEX
    Explanations

    pronoun subjects of verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åķĨ
    -0.20
    ç»Ĩç»Ĩ
    -0.18
    nal
    -0.18
    obl
    -0.18
     OST
    -0.17
    ite
    -0.17
     relevant
    -0.17
    ror
    -0.17
    imap
    -0.17
    nement
    -0.17
    POSITIVE LOGITS
    帮ä»ĸ
    0.26
    让ä»ĸ
    0.24
     him
    0.24
    ä»ĸæĽ¾
    0.23
    åijĬè¯īä»ĸ
    0.23
    çľĭä»ĸ
    0.23
    ä»ĸåıĪ
    0.23
    ç»Ļä»ĸ
    0.22
    him
    0.21
     próprio
    0.20
    Activations Density 0.152%

    No Known Activations