© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17301
    Prev
    Next
    INDEX
    Explanations

    thoughts, thinking, dreams, mind

    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
    Negative Logits
    ÑĩаÑĤ
    -0.20
    elier
    -0.19
    iap
    -0.19
     Positioned
    -0.18
     Everywhere
    -0.18
    æ´»åĬĽ
    -0.18
    æ£ĺ
    -0.18
    aran
    -0.18
    jun
    -0.18
    缸è§ģ
    -0.18
    POSITIVE LOGITS
     thoughts
    0.39
    念头
    0.29
    ðŁĴŃ
    0.24
    æĥ³æ³ķ
    0.24
     Thoughts
    0.23
    æı£
    0.22
    æĢĿ绪
    0.21
    èĦijæµ·
    0.21
    é»ĺ
    0.21
     thought
    0.21
    Activations Density 0.111%

    No Known Activations