© 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. 10880
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by 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
    å½ĵä¸ĭ
    -0.20
    èĦijåŃIJéĩĮ
    -0.20
    ä¸įæĸŃåľ°
    -0.19
     Aspect
    -0.19
    å°ıåŃ©åŃIJ
    -0.19
    å¥ijåIJĪ
    -0.19
     Ivan
    -0.19
    oker
    -0.19
    è¯Ħå®ļ
    -0.19
    åĺ´
    -0.18
    POSITIVE LOGITS
    å±¥
    0.21
    èµ´
    0.21
    dings
    0.20
    Accessor
    0.19
    彩èĻ¹
    0.19
    acers
    0.18
    gress
    0.17
    oot
    0.17
    /antlr
    0.17
    åij½è¿IJ
    0.17
    Activations Density 0.014%

    No Known Activations