© 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. 12976
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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
    odd
    -0.21
    æļĦ
    -0.20
    grass
    -0.20
    diamond
    -0.20
     Horn
    -0.20
    äºĶåħŃ
    -0.20
    anka
    -0.20
    èįī
    -0.19
    ?url
    -0.19
    ä¸Ģ缴éĥ½æĺ¯
    -0.19
    POSITIVE LOGITS
    æµ´
    0.21
    ç»ĪçĶŁ
    0.20
    æ£Ģçĸ«
    0.19
    è°¥
    0.19
    社ä¼ļåĮĸ
    0.19
     tan
    0.19
    æıIJçĤ¼
    0.18
    祯
    0.18
    èĥ¸
    0.18
    æŃ»åIJİ
    0.18
    Activations Density 0.122%

    No Known Activations