© 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. 12702
    Prev
    Next
    INDEX
    Explanations

    inevitable consequences

    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
    ening
    -0.18
    èĮ«
    -0.18
    èģĤ
    -0.18
    åįĥä¸ĩåĪ«
    -0.17
    ä¸ĵ享
    -0.17
    ernes
    -0.17
    erve
    -0.16
    ä¸Ģ年级
    -0.16
    å¾Īæľī
    -0.16
     nowrap
    -0.16
    POSITIVE LOGITS
    mente
    0.29
    æľīä¸Ģ天
    0.22
    çĦ¶æĺ¯
    0.21
    ity
    0.19
    -looking
    0.19
     (?)
    0.19
    idades
    0.18
    ously
    0.18
    itous
    0.18
    lich
    0.18
    Activations Density 0.008%

    No Known Activations