© 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. 12834
    Prev
    Next
    INDEX
    Explanations

    Adam, Eve, sin, fruit, fall

    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
    è´¡çĮ®
    -0.22
    łģ
    -0.21
    岿
    -0.21
    豫
    -0.19
    è¡Ĺ
    -0.19
    éŃĶæ³ķå¸Ī
    -0.19
    鸱
    -0.19
    Ajax
    -0.19
    ä¸ļä½Ļ
    -0.19
    oge
    -0.18
    POSITIVE LOGITS
     Adam
    0.25
    Adam
    0.22
    esis
    0.22
    ç¦ģ
    0.22
    éĢł
    0.22
    第ä¸Ģ次
    0.21
    ç¾İ好çļĦ
    0.20
    æķĻè®Ń
    0.20
     fruit
    0.19
     spinach
    0.19
    Activations Density 0.013%

    No Known Activations