© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    possessive 's and 're

    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
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.23
    讫
    -0.20
    è¿Ļä¸ĢåĪĩ
    -0.20
    ians
    -0.20
    åı²è¯Ĺ
    -0.19
    _Enter
    -0.19
    ä¸ĢåĪĩéĥ½
    -0.19
    иÑĩеÑģкие
    -0.18
    SIDE
    -0.18
    ius
    -0.18
    POSITIVE LOGITS
    æĿł
    0.20
     Yun
    0.20
    æĥ³èµ·æĿ¥
    0.20
    .pk
    0.20
    éĢĤçĶ¨äºİ
    0.19
    Occurs
    0.19
    åį´æĺ¯
    0.19
    åŁĭ
    0.19
    åŃĺåľ¨äºİ
    0.19
     Pad
    0.18
    Activations Density 0.131%

    No Known Activations