© 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. 14638
    Prev
    Next
    INDEX
    Explanations

    military units

    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§ijæĬĢèĤ¡ä»½
    -0.20
    æŶèĬĤ
    -0.19
    好çİ©
    -0.19
    æ§ģ
    -0.19
    ä½ľä¸ºä¸ĢåIJį
    -0.18
    ances
    -0.18
    umes
    -0.18
    èĤ¤
    -0.18
    curity
    -0.17
    å§IJå§IJ
    -0.17
    POSITIVE LOGITS
    è§Ħ模
    0.23
    -level
    0.22
    -scale
    0.22
    份
    0.21
    apter
    0.20
    åĨħçļĦ
    0.20
    æĪIJç«ĭ以æĿ¥
    0.20
     trÆ°á»Łng
    0.19
    级åĪ«çļĦ
    0.19
    éĻIJé¢Ŀ
    0.19
    Activations Density 0.025%

    No Known Activations