© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    color and colour saturation

    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
    å¾Ĵ
    -0.21
    çļĦåIJįåŃĹ
    -0.20
    便æ°ij
    -0.19
    çĻ½èī²
    -0.19
    èıĮ
    -0.19
    æĽĪ
    -0.19
    梯
    -0.18
    主æĦı
    -0.18
    çĻ½èī²çļĦ
    -0.18
    åı¹æģ¯
    -0.18
    POSITIVE LOGITS
    åĩĨç¡®
    0.22
    èĶ¬
    0.20
     Gardens
    0.20
    é²ľèī³
    0.19
    æķ´è½¦
    0.19
    æĪIJ份
    0.18
    è¡Į驶
    0.18
    lov
    0.18
    纯åĩĢ
    0.18
    ä»ĩ
    0.17
    Activations Density 0.011%

    No Known Activations