© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    vehicle types and models

    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
    åħ¨è¦ĨçĽĸ
    -0.23
     iT
    -0.20
    ith
    -0.20
    ä¸Ģæľµ
    -0.20
    éĺµéĺµ
    -0.19
    çľ¼æ³ª
    -0.19
    æ§Į
    -0.19
    ä¸Ģçĵ¶
    -0.19
     cloud
    -0.19
    azzi
    -0.19
    POSITIVE LOGITS
    åİŁåŀĭ
    0.37
    ç³»åĪĹ
    0.24
    /loader
    0.24
    æ¼Ķåıĺ
    0.23
    æĹ¶æľŁçļĦ
    0.23
    èĭıèģĶ
    0.23
    åIJİæľŁ
    0.23
    æľĢæĹ©çļĦ
    0.23
    å°ıåŀĭ
    0.22
    åĽ¾çº¸
    0.22
    Activations Density 0.131%

    No Known Activations