© 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. 17305
    Prev
    Next
    INDEX
    Explanations

    disabled people and access

    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
    Negative Logits
    OrUpdate
    -0.20
    å¨ĺ
    -0.19
    -vertical
    -0.19
    åīĬ
    -0.18
    蹿
    -0.18
    æ²īæµ¸åľ¨
    -0.18
    çıłä¸īè§Ĵ
    -0.18
    æįī
    -0.17
    cura
    -0.17
    olen
    -0.17
    POSITIVE LOGITS
    人士
    0.23
    åĦ¿ç«¥
    0.20
    æ®ĭçĸ¾
    0.20
    odus
    0.20
    /dis
    0.18
    itter
    0.18
    friendly
    0.18
    é¢ĺæĿIJ
    0.18
     limb
    0.18
    anst
    0.18
    Activations Density 0.025%

    No Known Activations