© 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. 12292
    Prev
    Next
    INDEX
    Explanations

    social media users

    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
    åįıè°ĥ
    -0.21
    没æĶ¶
    -0.20
    ä¸ĢåĪĨéĴŁ
    -0.20
    çķĻç»Ļ
    -0.20
    ä¹İ
    -0.20
     stro
    -0.19
    éĢĤåIJĪ
    -0.19
    åĬ±å¿Ĺ
    -0.19
    ä¸İåIJ¦
    -0.19
    ä¸ĢåĪĨ
    -0.18
    POSITIVE LOGITS
    å¢ŀéķ¿çİĩ
    0.26
    人æķ°
    0.23
    adies
    0.21
    èIJİ缩
    0.21
    è§Ħ模
    0.20
     worldwide
    0.20
    æķ°éĩı
    0.20
    人群
    0.19
     betrayed
    0.19
    å¢ŀéķ¿
    0.19
    Activations Density 0.032%

    No Known Activations