© 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. 13038
    Prev
    Next
    INDEX
    Explanations

    muscle cars

    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
    åķĦ
    -0.23
    èĬ¥
    -0.21
    æ¸ħæĸ°
    -0.20
    åĴĮçĿ¦
    -0.20
    è¯Ļ
    -0.20
    å©Ĩ
    -0.19
    ç¾¼
    -0.19
    greens
    -0.19
    çijŀ士
    -0.18
    åĴķ
    -0.18
    POSITIVE LOGITS
     swagger
    0.24
    åį
    0.23
     Auburn
    0.23
    индивид
    0.22
     Shelby
    0.20
    å®ŀ
    0.20
    индив
    0.20
    åĪ»
    0.20
    çĬĬ
    0.20
    æī«é»ijéĻ¤æģ¶
    0.19
    Activations Density 0.014%

    No Known Activations