© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    charge munitions

    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
    ç«¥
    -0.24
    uess
    -0.21
    æºIJæºIJä¸įæĸŃ
    -0.21
    社ä¼ļåĮĸ
    -0.20
    Raster
    -0.20
    çłº
    -0.19
     Loot
    -0.19
    flags
    -0.19
    貫
    -0.19
    æĬ½åĩº
    -0.19
    POSITIVE LOGITS
     shaped
    0.22
    ç»ĵæŀĦè°ĥæķ´
    0.21
    å½¢çĬ¶
    0.20
    ç»ĵæŀĦ
    0.20
    chaft
    0.20
    æŀ¶æŀĦ
    0.19
    ence
    0.19
    交åıī
    0.19
    æ²ī
    0.19
    urgy
    0.19
    Activations Density 0.215%

    No Known Activations