© 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. 15675
    Prev
    Next
    INDEX
    Explanations

    Patent Appeals

    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
    çīĩåĪ»
    -0.21
    Spl
    -0.21
     MULTI
    -0.21
    æľºåĬ¨
    -0.19
    éĺŁåijĺ们
    -0.19
    å¯Įæ°ij
    -0.18
    第ä¸ĢæŃ¥
    -0.18
    çŃ¹çłģ
    -0.18
    ÑİÑĢ
    -0.18
    çķĪ
    -0.18
    POSITIVE LOGITS
    åIJİèĢħ
    0.24
    èĦļä¸ĭ
    0.20
    åħij
    0.20
    æ¸Ń
    0.19
    é¼ĵ
    0.19
    æµĵæµĵ
    0.19
    gressor
    0.18
    åħ±åIJĮ
    0.18
    èĤ¡
    0.18
     tah
    0.18
    Activations Density 0.506%

    No Known Activations