© 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. 13504
    Prev
    Next
    INDEX
    Explanations

    prepositions like in and on

    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
    è¿Ļ对
    -0.25
    uela
    -0.23
    creasing
    -0.22
    åıªè¦ģæĺ¯
    -0.21
    è¿Ļæł·çļĦè¯Ŀ
    -0.20
    åıªè¦ģä½ł
    -0.20
    ObjectType
    -0.19
    竦
    -0.18
    VRT
    -0.18
    ivia
    -0.17
    POSITIVE LOGITS
    æŁIJç§įç¨ĭ度
    0.20
    est
    0.20
     cui
    0.20
    ä½ķå¤Ħ
    0.18
    è¿ĺå°Ĩ
    0.18
    轨
    0.18
    å°ıäºĭ
    0.17
    å°ıåѦçĶŁ
    0.17
    lines
    0.17
    å³Ļ
    0.17
    Activations Density 0.264%

    No Known Activations