© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10662
    Prev
    Next
    INDEX
    Explanations

    love word detection

    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
    æĤį
    -0.20
    çĨı
    -0.19
    渡
    -0.19
    tá
    -0.18
    æ®Ĭ
    -0.18
    æĭĺ
    -0.18
    ukt
    -0.17
    kok
    -0.17
    ç´
    -0.17
    rud
    -0.17
    POSITIVE LOGITS
    able
    0.21
    leen
    0.21
    IMIT
    0.18
    -worthy
    0.18
    åħ¶æīĢ
    0.18
    CAST
    0.18
    大çīĩ
    0.17
    æ°IJ
    0.17
    exter
    0.17
    ingly
    0.16
    Activations Density 0.008%

    No Known Activations