© 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. 14103
    Prev
    Next
    INDEX
    Explanations

    company and firm names

    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
    æį»
    -0.20
    ëł¹
    -0.20
    ä½ľä¸ºä¸ĢåIJį
    -0.19
    ниÑĩ
    -0.19
    è¿Ļåħ¶ä¸Ń
    -0.19
    ë³Ģ
    -0.18
    身æĹģ
    -0.18
    æĺ¯ä¸Ģéĥ¨
    -0.18
    èĮ«èĮ«
    -0.17
     long
    -0.17
    POSITIVE LOGITS
    巨头
    0.21
    æľºæŀĦ
    0.21
    åIJį为
    0.20
    å¤ļæĸ¹
    0.20
    åĽĽæĸ¹
    0.20
    åı«åģļ
    0.19
    åħ¬åı¸å°Ĩ
    0.19
     Odds
    0.19
    å¯ĵ
    0.19
    uve
    0.18
    Activations Density 0.068%

    No Known Activations