© 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. 11657
    Prev
    Next
    INDEX
    Explanations

    content specific nouns

    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
    éĩį度
    -0.18
    ä»İä¸Ń
    -0.18
    anco
    -0.18
    æŁ¬
    -0.18
    åĹ£
    -0.18
     indeed
    -0.18
    åĨľ
    -0.17
    æŁıæŀĹ
    -0.17
    ÅĤa
    -0.17
    æīĩ
    -0.17
    POSITIVE LOGITS
     ÙĪاÙĦتÙĬ
    0.25
    /projects
    0.21
     ÙĪاÙĦØ°ÙĬ
    0.21
    æ¯ıä¸Ģ天
    0.20
    /on
    0.19
    èĢĮ导èĩ´
    0.19
    óst
    0.19
    çļĦåIJĦ项
    0.19
    åIJĦ项
    0.18
    æīĢåģļçļĦ
    0.18
    Activations Density 0.378%

    No Known Activations