© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 11030
    Prev
    Next
    INDEX
    Explanations

    vehicle handling and performance

    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
    æľį
    -0.25
    åĶ®åįĸ
    -0.24
    请åģĩ
    -0.23
    ledon
    -0.23
     pled
    -0.22
    æ¯ĽåŃĶ
    -0.22
    éĴĮ
    -0.21
    æ¯ı人
    -0.21
    å¥ijæľº
    -0.20
    éļıåį³
    -0.20
    POSITIVE LOGITS
    æĢ§èĥ½
    0.41
    平衡
    0.32
    é«ĺæĢ§èĥ½
    0.29
     performance
    0.29
    éĢŁåº¦
    0.28
    è½»
    0.26
    è¼ķ
    0.25
    åı¯éĿłçļĦ
    0.25
    æĺ¯ä¸Ģ款
    0.25
     speed
    0.24
    Activations Density 0.037%

    No Known Activations