© 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. 12806
    Prev
    Next
    INDEX
    Explanations

    year in a row

    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
    Mapper
    -0.22
    åĽĽçº§
    -0.21
    便åĪ©
    -0.21
    èµ·æŃ¥
    -0.20
    对å¾ħ
    -0.20
    åĩı
    -0.20
    æīĵåĩ»
    -0.20
    ä¸İåħ¶
    -0.19
    æ¸Ľ
    -0.18
    ç»Ħç»ĩå®ŀæĸ½
    -0.18
    POSITIVE LOGITS
    èĥľè´Ł
    0.35
    winner
    0.34
     winner
    0.33
    赢家
    0.31
    Winner
    0.31
    åģıåIJij
    0.31
     dominance
    0.29
    è°ģ
    0.27
    äºī夺
    0.27
     Winner
    0.27
    Activations Density 0.221%

    No Known Activations