© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    disaster and severe weather events

    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
    éĽªèĬ±
    -0.22
    è¾Ħ
    -0.21
    èĪįå¾Ĺ
    -0.20
     winters
    -0.20
    ç»Ĩç»Ĩ
    -0.19
    çIJ¢ç£¨
    -0.19
    Ñģел
    -0.19
    ä¸Ģä¸Ŀ
    -0.19
    被人
    -0.19
    ç»ĩ
    -0.18
    POSITIVE LOGITS
    å¯ĨåĪĩ
    0.21
    agher
    0.21
    èĪIJ
    0.21
    oston
    0.19
    åĹĴ
    0.19
    èķī
    0.19
    åįļ
    0.18
    å½±åĵį
    0.18
    æĥħåĨµ
    0.18
    nia
    0.18
    Activations Density 0.084%

    No Known Activations