© 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. 13198
    Prev
    Next
    INDEX
    Explanations

    intentions or intent

    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
    stral
    -0.20
    详ç»Ĩä»ĭç»į
    -0.20
    形容
    -0.20
    èĹĵ
    -0.19
    nable
    -0.19
    tee
    -0.19
    æĬĢæľ¯æ°´å¹³
    -0.19
    èĪĮå°ĸ
    -0.18
    çļĦæĢ§æł¼
    -0.18
    褫
    -0.18
    POSITIVE LOGITS
    æĦıåĽ¾
    0.28
     intent
    0.27
    intent
    0.25
    Intent
    0.23
     intentions
    0.21
     Intent
    0.20
    _intent
    0.20
    æľīè¿Ļæł·çļĦ
    0.20
    æŁIJæŁIJ
    0.20
    éĩįè§Ĩ
    0.20
    Activations Density 0.076%

    No Known Activations