© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12391
    Prev
    Next
    INDEX
    Explanations

    telescopes and space satellites

    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
    èѦåĬ¡
    -0.20
    åľ¨åºĬä¸Ĭ
    -0.20
    人æ°ijéĵ¶è¡Į
    -0.20
    ãĤ³ãĥĶãĥ¼
    -0.19
    åIJĪåĩ»
    -0.19
    ioned
    -0.19
    俸
    -0.18
    åĪĪ
    -0.18
     nghiá»ĩp
    -0.18
    iaz
    -0.17
    POSITIVE LOGITS
    æ¸ļ
    0.23
    æľĽ
    0.22
    ç¢į
    0.22
    æĤ¬å´ĸ
    0.22
    æ·Ģ
    0.20
    æĥij
    0.20
    çĪ·
    0.20
    äºī
    0.20
    æĪĸèĢħåħ¶ä»ĸ
    0.20
    å¼ºåĽ½
    0.19
    Activations Density 0.006%

    No Known Activations