© 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. 17289
    Prev
    Next
    INDEX
    Explanations

    dangers and hazards

    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
    ä¸ĢåĽ¢
    -0.17
    ä¼łè¨Ģ
    -0.16
     borderBottom
    -0.16
    ç´§åĩij
    -0.16
    simp
    -0.15
    gon
    -0.15
    ãģĦãĤį
    -0.15
    ä¸ļä½Ļ
    -0.15
    urat
    -0.15
     Rehabilitation
    -0.15
    POSITIVE LOGITS
     risks
    0.21
    æīĢåľ¨
    0.20
     posed
    0.20
     dangers
    0.20
    éĩįéĩį
    0.19
     indo
    0.18
    éļIJæĤ£
    0.18
    麽
    0.18
    /problem
    0.18
    less
    0.17
    Activations Density 0.018%

    No Known Activations