© 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. 10674
    Prev
    Next
    INDEX
    Explanations

    representatives will assist

    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
    isma
    -0.20
    uploads
    -0.19
    使çĶ¨èĢħ
    -0.18
    ä¸ŃçļĦ
    -0.18
    orsch
    -0.18
    æµģè¡ĮçļĦ
    -0.18
    çĶŃ
    -0.18
     bull
    -0.18
    shal
    -0.18
    èĿĩ
    -0.18
    POSITIVE LOGITS
    详ç»ĨäºĨ解
    0.23
    å±ĬæŶ
    0.22
    è°Īè¯Ŀ
    0.22
    æł¸å®ŀ
    0.21
    çµ®
    0.21
    客æĪ·æľįåĬ¡
    0.21
    客æľį
    0.21
    çĥŃ线
    0.21
    ëĭĺ
    0.20
    èĺ¸
    0.20
    Activations Density 0.017%

    No Known Activations